Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Abstract

We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at https://github.com/zalandoresearch/fashion-mnist

arXiv commentDataset is freely available at https://github.com/zalandoresearch/fashion-mnist Benchmark is available at http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/

References in corpus (1)

• EMNIST: an extension of MNIST to handwritten letters

Cited by in corpus (1450)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Deep Learning using Rectified Linear Units (ReLU)
• Random Erasing Data Augmentation
• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• Deep Anomaly Detection Using Geometric Transformations
• Analyzing Federated Learning through an Adversarial Lens
• Prevalence of Neural Collapse during the terminal phase of deep learning training
• Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data
• Fair Resource Allocation in Federated Learning
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• Sensitivity and Generalization in Neural Networks: an Empirical Study
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Deep Embedded Multi-view Clustering with Collaborative Training
• Agnostic Federated Learning
• Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks
• Self-Supervised Discriminative Feature Learning for Deep Multi-View Clustering
• Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization
• A Survey of Privacy Attacks in Machine Learning
• Three Factors Influencing Minima in SGD
• Overcoming catastrophic forgetting with hard attention to the task
• Ditto: Fair and Robust Federated Learning Through Personalization
• Quantum machine learning beyond kernel methods
• A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule
• The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
• Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
• On Empirical Comparisons of Optimizers for Deep Learning
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges
• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Towards Robust Evaluations of Continual Learning
• L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
• SpinalNet: Deep Neural Network with Gradual Input
• Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
• Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Things
• Misalignment Resilient Diffractive Optical Networks
• Analysis and Optimal Edge Assignment For Hierarchical Federated Learning on Non-IID Data
• Measuring the Effects of Data Parallelism on Neural Network Training
• Measuring Calibration in Deep Learning
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Multimodal Generative Models for Scalable Weakly-Supervised Learning
• An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification
• Input complexity and out-of-distribution detection with likelihood-based generative models
• Peer-to-peer Federated Learning on Graphs
• Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
• How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
• Deep Multiview Clustering by Contrasting Cluster Assignments
• Constructing Unrestricted Adversarial Examples with Generative Models
• Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
• Knowledge Distillation in Deep Learning and its Applications
• Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
• Lifelong Generative Modeling
• Deep learning generalizes because the parameter-function map is biased towards simple functions
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• A Comprehensive Survey of Dataset Distillation
• Review: Deep Learning in Electron Microscopy
• Flower: A Friendly Federated Learning Research Framework
• Dataset Condensation with Gradient Matching
• One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
• Explainable Deep One-Class Classification
• Interference Management for Over-the-Air Federated Learning in Multi-Cell Wireless Networks
• Sharpness-Aware Minimization for Efficiently Improving Generalization
• Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
• FMix: Enhancing Mixed Sample Data Augmentation
• Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder
• Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering
• Kernel Flows: from learning kernels from data into the abyss
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• One-Class Classification: A Survey
• The Conditional Entropy Bottleneck
• Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication
• Capsule Networks against Medical Imaging Data Challenges
• Learning and Evaluating Representations for Deep One-class Classification
• Neural Predictor based Quantum Architecture Search
• Shaping the learning landscape in neural networks around wide flat minima
• Diagnosing and Enhancing VAE Models
• To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Coresets via Bilevel Optimization for Continual Learning and Streaming
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Improving the Generalization of Adversarial Training with Domain Adaptation
• Auto-Keras: An Efficient Neural Architecture Search System
• Evolving Deep Convolutional Neural Networks for Image Classification
• An end-to-end trainable hybrid classical-quantum classifier
• Deep Polynomial Neural Networks
• Federated Learning on Non-IID Data Silos: An Experimental Study
• Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
• Quantum Algorithms for Deep Convolutional Neural Networks
• Inference Suboptimality in Variational Autoencoders
• Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
• Dive into Deep Learning
• Enhanced Convolutional Neural Tangent Kernels
• FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
• A Survey of Vectorization Methods in Topological Data Analysis
• FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning
• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• LEEP: A New Measure to Evaluate Transferability of Learned Representations
• An Efficient and Reliable Asynchronous Federated Learning Scheme for Smart Public Transportation
• Auditing Differentially Private Machine Learning: How Private is Private SGD?
• A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
• Task Agnostic Continual Learning Using Online Variational Bayes
• Improving Fairness for Data Valuation in Horizontal Federated Learning
• Automated tuning of double quantum dots into specific charge states using neural networks
• Geometric Dataset Distances via Optimal Transport
• Differentially Private Learning Needs Better Features (or Much More Data)
• An Electro-Photonic System for Accelerating Deep Neural Networks
• A Clustering-guided Contrastive Fusion for Multi-view Representation Learning
• Classical-to-quantum convolutional neural network transfer learning
• SpaceNet: Make Free Space For Continual Learning
• Performance-Efficiency Trade-off of Low-Precision Numerical Formats in Deep Neural Networks
• ASAP: Architecture Search, Anneal and Prune
• Lifelong Teacher-Student Network Learning
• Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes
• Controlling Neural Level Sets
• Learning Combinations of Activation Functions
• Supervised Learning with Projected Entangled Pair States
• Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
• How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks
• Maximal Jacobian-based Saliency Map Attack
• Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning
• Mitigating Backdoor Attacks in Federated Learning
• Do We Need Zero Training Loss After Achieving Zero Training Error?
• ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion
• EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
• DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection
• Data class-specific all-optical transformations and encryption
• Learning Disentangled Joint Continuous and Discrete Representations
• Learning curves of generic features maps for realistic datasets with a teacher-student model
• Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
• High Accuracy and High Fidelity Extraction of Neural Networks
• Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning
• Dataset Condensation with Differentiable Siamese Augmentation
• Provably Consistent Partial-Label Learning
• Understanding and Improving Early Stopping for Learning with Noisy Labels
• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
• Compressed Domain Image Classification Using a Dynamic-Rate Neural Network
• Disentangling feature and lazy training in deep neural networks
• Data Poisoning Attacks Against Federated Learning Systems
• AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning
• Adversarial Examples in Modern Machine Learning: A Review
• Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
• A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
• Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching
• On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
• Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream
• Generative Tensor Network Classification Model for Supervised Machine Learning
• Optimal Regularization Can Mitigate Double Descent
• DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
• Poisoning Attacks with Generative Adversarial Nets
• The Convolutional Tsetlin Machine
• Characterizing the Decision Boundary of Deep Neural Networks
• Superposition of many models into one
• Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-aided Over-the-Air Federated Learning
• Asynchronous Federated Learning on Heterogeneous Devices: A Survey
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
• Out-of-distribution Detection in Classifiers via Generation
• Dense and Diverse Capsule Networks: Making the Capsules Learn Better
• Photonic convolutional neural networks using integrated diffractive optics
• Understanding the impact of entropy on policy optimization
• Attribute Restoration Framework for Anomaly Detection
• Adversarial Examples - A Complete Characterisation of the Phenomenon
• Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning
• Entangled Watermarks as a Defense against Model Extraction
• High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
• Hierarchically Fair Federated Learning
• Why is the Mahalanobis Distance Effective for Anomaly Detection?
• Deep Weighted Averaging Classifiers
• FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation
• A black-box adversarial attack for poisoning clustering
• A simple and efficient architecture for trainable activation functions
• Learning a Code: Machine Learning for Approximate Non-Linear Coded Computation
• MNIST-MIX: A Multi-language Handwritten Digit Recognition Dataset
• Denoising Autoencoders for Overgeneralization in Neural Networks
• AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption
• Accelerated physical emulation of Bayesian inference in spiking neural networks
• On the Origin of Implicit Regularization in Stochastic Gradient Descent
• Label Noise Types and Their Effects on Deep Learning
• Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
• An Improved Evaluation Framework for Generative Adversarial Networks
• Online Coreset Selection for Rehearsal-based Continual Learning
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification
• Capsule Networks with Max-Min Normalization
• A framework for the extraction of Deep Neural Networks by leveraging public data
• Learning an Adaptive Learning Rate Schedule
• Finite Versus Infinite Neural Networks: an Empirical Study
• A Large Dimensional Analysis of Least Squares Support Vector Machines
• NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks
• Ensemble learning in CNN augmented with fully connected subnetworks
• BourGAN: Generative Networks with Metric Embeddings
• Predicting Neural Network Accuracy from Weights
• Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
• Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
• Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines
• Unsupervised Outlier Detection using Memory and Contrastive Learning
• Progressive Identification of True Labels for Partial-Label Learning
• Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Online Continual Learning on Sequences
• FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
• DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Measuring and Explaining the Inter-Cluster Reliability of Multidimensional Projections
• Fuzzy Pooling
• Online Normalization for Training Neural Networks
• Decentralized and Robust Privacy-Preserving Model Using Blockchain-Enabled Federated Deep Learning in Intelligent Enterprises
• Quantum Superposition Inspired Spiking Neural Network
• Finding Competitive Network Architectures Within a Day Using UCT
• L_DMI: An Information-theoretic Noise-robust Loss Function
• Similarity-based Label Inference Attack against Training and Inference of Split Learning
• Hyperparameter Ensembles for Robustness and Uncertainty Quantification
• Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
• An Investigation of Replay-based Approaches for Continual Learning
• Toward Understanding Catastrophic Forgetting in Continual Learning
• A Theoretical Framework for Target Propagation
• LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
• A Lightweight and Secure Deep Learning Model for Privacy-Preserving Federated Learning in Intelligent Enterprises
• Federated Continual Learning with Weighted Inter-client Transfer
• Edge-assisted Democratized Learning Towards Federated Analytics
• Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbations
• Tensor Normalization and Full Distribution Training
• Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
• The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
• AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devices
• Instance-dependent Label-noise Learning under a Structural Causal Model
• Federated Continual Learning: Concepts, Challenges, and Solutions
• Probabilistic Autoencoder
• Learning the Pareto Front with Hypernetworks
• Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images
• Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
• Tensor-based algorithms for image classification
• LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks
• Federated Learning Meets Multi-objective Optimization
• GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
• Regularizing Neural Network Training via Identity-wise Discriminative Feature Suppression
• The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size
• An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
• Efficient Continual Learning with Modular Networks and Task-Driven Priors
• FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers
• Federated Learning with Compression: Unified Analysis and Sharp Guarantees
• Into the Unknown: Active Monitoring of Neural Networks
• The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
• Outside the Box: Abstraction-Based Monitoring of Neural Networks
• AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification
• Robustness of Bayesian Neural Networks to Gradient-Based Attacks
• Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
• Perceptual Image Anomaly Detection
• CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
• Continual Learning with Adaptive Weights (CLAW)
• Feature Space Singularity for Out-of-Distribution Detection
• Variational quantum one-class classifier
• Defining Benchmarks for Continual Few-Shot Learning
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis
• Decentralized federated learning of deep neural networks on non-iid data
• Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning
• Structured and Unstructured Outlier Identification for Robust PCA: A Non iterative, Parameter free Algorithm
• Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data
• Sub-Architecture Ensemble Pruning in Neural Architecture Search
• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
• SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
• A Four-Pronged Defense Against Byzantine Attacks in Federated Learning
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates
• Bridging Adversarial Robustness and Gradient Interpretability
• Parameterized Knowledge Transfer for Personalized Federated Learning
• LDP-Fed: Federated Learning with Local Differential Privacy
• Decentralized Bayesian Learning over Graphs
• Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space
• Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
• HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• Learning Generative Models across Incomparable Spaces
• Resolution learning in deep convolutional networks using scale-space theory
• The Limitations of Model Uncertainty in Adversarial Settings
• Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity
• Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
• Bayesian Neural Network Priors Revisited
• Regular Polytope Networks
• On the Iteration Complexity of Hypergradient Computation
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Learning with Multiple Complementary Labels
• Visualizing Quantum Phases And Identifying Quantum Phase Transitions By Nonlinear Dimensionality Reduction
• Stochastic Domain Wall-Magnetic Tunnel Junction Artificial Neurons for Noise-Resilient Spiking Neural Networks
• Ultrafast single-channel machine vision based on neuro-inspired photonic computing
• A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
• QUILT: Effective Multi-Class Classification on Quantum Computers Using an Ensemble of Diverse Quantum Classifiers
• Scalable Rule-Based Representation Learning for Interpretable Classification
• Viewmaker Networks: Learning Views for Unsupervised Representation Learning
• XNAS: Neural Architecture Search with Expert Advice
• Robust Compressive Phase Retrieval via Deep Generative Priors
• Learning Interpretable Rules for Scalable Data Representation and Classification
• Multi-Edge Server-Assisted Dynamic Federated Learning with an Optimized Floating Aggregation Point
• Adversarial Machine Learning: Bayesian Perspectives
• Conducting Credit Assignment by Aligning Local Representations
• Class-constrained t-SNE: Combining Data Features and Class Probabilities
• Virus-MNIST: A Benchmark Malware Dataset
• NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
• Controllable Pareto Multi-Task Learning
• When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks
• Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
• Dataset Distillation with Infinitely Wide Convolutional Networks
• How Does Mixup Help With Robustness and Generalization?
• Lightweight Residual Densely Connected Convolutional Neural Network
• A Topological Machine Learning Pipeline for Classification
• Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning
• Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation
• Greedy Shapley Client Selection for Communication-Efficient Federated Learning
• Dense Hebbian neural networks: a replica symmetric picture of supervised learning
• CLIP: Cheap Lipschitz Training of Neural Networks
• Uniform Manifold Approximation with Two-phase Optimization
• Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
• Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Deep Learning Through the Lens of Example Difficulty
• A Neural Scaling Law from the Dimension of the Data Manifold
• Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
• SFE-GACN: A Novel Unknown Attack Detection Method Using Intra Categories Generation in Embedding Space
• Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks
• A Less Biased Evaluation of Out-of-distribution Sample Detectors
• A Brain-inspired Algorithm for Training Highly Sparse Neural Networks
• Exposing Reliability Degradation and Mitigation in Approximate DNNs under Permanent Faults
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• Neuromorphic Computing for Content-based Image Retrieval
• Regularization Shortcomings for Continual Learning
• SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks
• Task-Aware Variational Adversarial Active Learning
• Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications
• Multi-View Class Incremental Learning
• DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction
• Spiking neural networks trained via proxy
• Sparse Transfer Learning via Winning Lottery Tickets
• CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks
• Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
• Unsupervised Two-Stage Anomaly Detection
• Towards an Adversarially Robust Normalization Approach
• Croissant: A Metadata Format for ML-Ready Datasets
• Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective
• DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips
• Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
• DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
• Generative Latent Flow
• Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
• Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• A Random Matrix Analysis of Random Fourier Features: Beyond the Gaussian Kernel, a Precise Phase Transition, and the Corresponding Double Descent
• Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks
• Anomaly Detection with Tensor Networks
• Coalesced Multi-Output Tsetlin Machines with Clause Sharing
• SIMDive: Approximate SIMD Soft Multiplier-Divider for FPGAs with Tunable Accuracy
• Some Theoretical Insights into Wasserstein GANs
• Gaussian Universality of Perceptrons with Random Labels
• QDoor: Exploiting Approximate Synthesis for Backdoor Attacks in Quantum Neural Networks
• Adversarial Infidelity Learning for Model Interpretation
• Continual Classification Learning Using Generative Models
• Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data
• ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples
• Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
• Scalable and Order-robust Continual Learning with Additive Parameter Decomposition
• A Gradient Boosting Approach for Training Convolutional and Deep Neural Networks
• Comparison Network for One-Shot Conditional Object Detection
• DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware
• The Tree Ensemble Layer: Differentiability meets Conditional Computation
• Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates
• Dynamic Hard Pruning of Neural Networks at the Edge of the Internet
• Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization
• Anomaly Awareness
• Active Testing: Sample-Efficient Model Evaluation
• Unsupervised Out-of-Distribution Detection with Batch Normalization
• Negative Momentum for Improved Game Dynamics
• Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
• Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
• Soft-Root-Sign Activation Function
• DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning
• Complementary-Label Learning for Arbitrary Losses and Models
• Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates
• Repulsive Deep Ensembles are Bayesian
• A scalable saliency-based Feature selection method with instance level information
• Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks
• Deep Learning Development Environment in Virtual Reality
• An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
• ARFED: Attack-Resistant Federated averaging based on outlier elimination
• EvoAAA: An evolutionary methodology for automated \neural autoencoder architecture search
• Semi-Supervised Learning by Label Gradient Alignment
• Mobility-Aware Decentralized Federated Learning with Joint Optimization of Local Iteration and Leader Selection for Vehicular Networks
• Learning under Model Misspecification: Applications to Variational and Ensemble methods
• Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
• Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy
• CDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learning
• Specialized federated learning using a mixture of experts
• ProdSumNet: reducing model parameters in deep neural networks via product-of-sums matrix decompositions
• Variational Autoencoders with Normalizing Flow Decoders
• Explaining Bayesian Neural Networks
• TriBYOL: Triplet BYOL for Self-Supervised Representation Learning
• Efficient computation and analysis of distributional Shapley values
• Robust Variational Autoencoder
• AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning
• Accurate and Fast Federated Learning via IID and Communication-Aware Grouping
• An Encoding Framework for Binarized Images using HyperDimensional Computing
• Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification
• Manas: Mining Software Repositories to Assist AutoML
• OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
• The Search for Sparse, Robust Neural Networks
• Waveguide-multiplexed photonic matrix-vector multiplication processor using multiport photodetectors
• Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution
• Coverage Testing of Deep Learning Models using Dataset Characterization
• On the Vulnerability of Capsule Networks to Adversarial Attacks
• Generative causal explanations of black-box classifiers
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• Dendrite Net: A White-Box Module for Classification, Regression, and System Identification
• Quick-CapsNet (QCN): A fast alternative to Capsule Networks
• PILAE: A Non-gradient Descent Learning Scheme for Deep Feedforward Neural Networks
• A Close Look at Deep Learning with Small Data
• Deep Active Learning: Unified and Principled Method for Query and Training
• Detecting Violations of Differential Privacy for Quantum Algorithms
• You Can Backdoor Personalized Federated Learning
• Semisupervised Anomaly Detection using Support Vector Regression with Quantum Kernel
• Membership Model Inversion Attacks for Deep Networks
• FedCos: A Scene-adaptive Federated Optimization Enhancement for Performance Improvement
• Using a thousand optimization tasks to learn hyperparameter search strategies
• Class Gradient Projection For Continual Learning
• Puzzle-AE: Novelty Detection in Images through Solving Puzzles
• To Ensemble or Not Ensemble: When does End-To-End Training Fail?
• On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers
• Frustratingly Easy Transferability Estimation
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• Brain-Inspired Hyperdimensional Computing: How Thermal-Friendly for Edge Computing?
• FathomNet: An underwater image training database for ocean exploration and discovery
• Towards Understanding the Transferability of Deep Representations
• Embedded hyper-parameter tuning by Simulated Annealing
• TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring
• Information flows of diverse autoencoders
• Deep machine learning for meteor monitoring: advances with transfer learning and gradient-weighted class activation mapping
• Efficient MPS representations and quantum circuits from the Fourier modes of classical image data
• Active Image Synthesis for Efficient Labeling
• Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
• Building robust classifiers through generation of confident out of distribution examples
• Distributional Generalization: A New Kind of Generalization
• Unified Adversarial Invariance
• Adversarial Detection and Correction by Matching Prediction Distributions
• Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
• Benchmarking Quantized Neural Networks on FPGAs with FINN
• Homogeneous Learning: Self-Attention Decentralized Deep Learning
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Evaluating the Robustness of Nearest Neighbor Classifiers: A Primal-Dual Perspective
• Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets
• Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
• Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense
• Capsule networks with non-iterative cluster routing
• The Hidden Uncertainty in a Neural Networks Activations
• Generalization bounds for deep learning
• Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions
• Neuron Merging: Compensating for Pruned Neurons
• Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection
• Image reconstruction through a multimode fiber with a simple neural network architecture
• Jointly Deep Multi-View Learning for Clustering Analysis
• Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima
• Variational Laplace Autoencoders
• Adaptive Sampling for Stochastic Risk-Averse Learning
• Can Single Neurons Solve MNIST? The Computational Power of Biological Dendritic Trees
• Rethinking Importance Weighting for Deep Learning under Distribution Shift
• Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
• Variant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices
• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
• Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
• How adversarial attacks can disrupt seemingly stable accurate classifiers
• Hyperparameter Auto-tuning in Self-Supervised Robotic Learning
• Predictive Uncertainty Quantification with Compound Density Networks
• Parity Models: A General Framework for Coding-Based Resilience in ML Inference
• Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain
• Secure Quantized Training for Deep Learning
• Bayesian Deep Learning via Subnetwork Inference
• Towards Self-Adaptive Metric Learning On the Fly
• E${}^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
• Sparsely Activated Networks
• Temporal Output Discrepancy for Loss Estimation-based Active Learning
• Quantum algorithms for SVD-based data representation and analysis
• PuVAE: A Variational Autoencoder to Purify Adversarial Examples
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Concise Explanations of Neural Networks using Adversarial Training
• Learning Optimal Conformal Classifiers
• An Unconstrained Layer-Peeled Perspective on Neural Collapse
• Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
• MMFashion: An Open-Source Toolbox for Visual Fashion Analysis
• Bayesian Learning of Neural Network Architectures
• Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification
• Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
• An Empirical Study of Large-Batch Stochastic Gradient Descent with Structured Covariance Noise
• CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
• Quantum support vector data description for anomaly detection
• Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
• Faster Non-Convex Federated Learning via Global and Local Momentum
• Alleviating Mode Collapse in GAN via Diversity Penalty Module
• Stateful Detection of Model Extraction Attacks
• Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
• Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations
• One-Shot Learning using Mixture of Variational Autoencoders: a Generalization Learning approach
• Learning disconnected manifolds: a no GANs land
• Coded Computing for Federated Learning at the Edge
• Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training
• Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
• Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis
• Annealing Genetic GAN for Minority Oversampling
• On-FPGA Training with Ultra Memory Reduction: A Low-Precision Tensor Method
• Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
• One-pixel Signature: Characterizing CNN Models for Backdoor Detection
• Automatic structured variational inference
• Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• State-Regularized Recurrent Neural Networks
• Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs
• A Framework for Deep Constrained Clustering -- Algorithms and Advances
• Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks
• Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
• One-Class Feature Learning Using Intra-Class Splitting
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
• Deep Density-based Image Clustering
• Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks
• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
• Do biological constraints impair dendritic computation?
• Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks
• Query-Efficient Black-Box Attack by Active Learning
• Jacobian Regularization for Mitigating Universal Adversarial Perturbations
• Fast Dynamic Routing Based on Weighted Kernel Density Estimation
• On the Necessity and Effectiveness of Learning the Prior of Variational Auto-Encoder
• Soft Gradient Boosting Machine
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
• SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders
• Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings
• Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation
• Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
• REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study
• Is a Classification Procedure Good Enough? A Goodness-of-Fit Assessment Tool for Classification Learning
• Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
• Express Wavenet -- a low parameter optical neural network with random shift wavelet pattern
• Activation Function Optimization Scheme for Image Classification
• RingFed: Reducing Communication Costs in Federated Learning on Non-IID Data
• Fast Inference in Capsule Networks Using Accumulated Routing Coefficients
• Identifying Mislabeled Images in Supervised Learning Utilizing Autoencoder
• Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) Networks
• Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack
• Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
• ESAD: End-to-end Deep Semi-supervised Anomaly Detection
• Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
• Unified Group Fairness on Federated Learning
• Towards Characterizing and Limiting Information Exposure in DNN Layers
• Deep Image Clustering with Category-Style Representation
• Impact of Feedback Type on Explanatory Interactive Learning
• Empirical study of extreme overfitting points of neural networks
• Smallify: Learning Network Size while Training
• Flexible Multi-task Networks by Learning Parameter Allocation
• Dynamic of Stochastic Gradient Descent with State-Dependent Noise
• SLIQ: Quantum Image Similarity Networks on Noisy Quantum Computers
• Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra
• Scaling Down Deep Learning with MNIST-1D
• The Geometry of Sign Gradient Descent
• Neural Architecture Search using Particle Swarm and Ant Colony Optimization
• Building Deep, Equivariant Capsule Networks
• Pushing the Limits of Capsule Networks
• Designing lensless imaging systems to maximize information capture
• Bayesian Inference with Certifiable Adversarial Robustness
• Meta Learning Backpropagation And Improving It
• Federated Learning with Intermediate Representation Regularization
• MMGAN: Generative Adversarial Networks for Multi-Modal Distributions
• Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
• AdvKnn: Adversarial Attacks On K-Nearest Neighbor Classifiers With Approximate Gradients
• Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker
• When and How Mixup Improves Calibration
• Detecting OODs as datapoints with High Uncertainty
• Hierarchical VAEs Know What They Don't Know
• Generalized Negative Correlation Learning for Deep Ensembling
• SwiftNet: Using Graph Propagation as Meta-knowledge to Search Highly Representative Neural Architectures
• Is SGD a Bayesian sampler? Well, almost
• FPGA Resource-aware Structured Pruning for Real-Time Neural Networks
• Bit Error Robustness for Energy-Efficient DNN Accelerators
• Disentangling and Learning Robust Representations with Natural Clustering
• Federated Learning on Non-iid Data via Local and Global Distillation
• Classification with Rejection Based on Cost-sensitive Classification
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• Towards Fair Federated Learning with Zero-Shot Data Augmentation
• Sequential Graph Convolutional Network for Active Learning
• KerCNNs: biologically inspired lateral connections for classification of corrupted images
• Towards Practical Watermark for Deep Neural Networks in Federated Learning
• ImmuNeCS: Neural Committee Search by an Artificial Immune System
• Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach
• Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Reducing Inference Energy Consumption Using Dual Complementary CNNs
• Adaptive Resolution Inference (ARI): Energy-Efficient Machine Learning for Internet of Things
• Identifying Classes Susceptible to Adversarial Attacks
• Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
• Second-Order Provable Defenses against Adversarial Attacks
• Constrained deep neural network architecture search for IoT devices accounting hardware calibration
• Approximate Byzantine Fault-Tolerance in Distributed Optimization
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality
• Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks
• Clustering-Oriented Representation Learning with Attractive-Repulsive Loss
• K-Splits: Improved K-Means Clustering Algorithm to Automatically Detect the Number of Clusters
• Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets
• Measuring and Harnessing Transference in Multi-Task Learning
• Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers
• Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization
• Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
• Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
• Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach
• Meta Feature Modulator for Long-tailed Recognition
• MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning
• Improving Deep Image Clustering With Spatial Transformer Layers
• Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
• Semantic-Based Neural Network Repair
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
• Deep convolutional tensor network
• Towards Metric DBSCAN: Exact, Approximate, and Streaming Algorithms
• Improving ClusterGAN Using Self-Augmented Information Maximization of Disentangling Latent Spaces
• Learning the Precise Feature for Cluster Assignment
• Adversarial Learning of General Transformations for Data Augmentation
• Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
• Robust Training in High Dimensions via Block Coordinate Geometric Median Descent
• An Efficient Adversarial Attack for Tree Ensembles
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
• Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network
• Interpretable Graph Capsule Networks for Object Recognition
• When Optimizing $f$-divergence is Robust with Label Noise
• Classifying the classifier: dissecting the weight space of neural networks
• Imbalanced Image Classification with Complement Cross Entropy
• Multimodal Generative Models for Compositional Representation Learning
• Performing Co-Membership Attacks Against Deep Generative Models
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
• Small Towers Make Big Differences
• On the Effectiveness of Regularization Against Membership Inference Attacks
• Long Short-Term Attention
• Approximating Instance-Dependent Noise via Instance-Confidence Embedding
• Gradient target propagation
• Bayesian Inference Forgetting
• AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
• Measuring Dependence with Matrix-based Entropy Functional
• Effects of Loss Functions And Target Representations on Adversarial Robustness
• The functional role of cue-driven feature-based feedback in object recognition
• Learning Hierarchical Priors in VAEs
• DeepOBS: A Deep Learning Optimizer Benchmark Suite
• Inductive Transfer for Neural Architecture Optimization
• Multi-VFL: A Vertical Federated Learning System for Multiple Data and Label Owners
• Context-Aware Multipath Networks
• Spiking Neural Predictive Coding for Continual Learning from Data Streams
• Adversarial Attack and Defense in Deep Ranking
• Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
• Understanding the Effect of Bias in Deep Anomaly Detection
• POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique
• A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation
• Evolutionary Multi-objective Optimisation in Neurotrajectory Prediction
• pFedGame -- Decentralized Federated Learning using Game Theory in Dynamic Topology
• Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering
• Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
• Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation
• Continuous Mixtures of Tractable Probabilistic Models
• Interaction Decompositions for Tensor Network Regression
• Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation
• Convolutional Neural Networks for Searching Superflares from Pixel-level Data of the Transiting Exoplanet Survey Satellite
• NeuNetS: An Automated Synthesis Engine for Neural Network Design
• Clustering a Mixture of Gaussians with Unknown Covariance
• Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
• Relative stability toward diffeomorphisms indicates performance in deep nets
• Causality-aware counterfactual confounding adjustment for feature representations learned by deep models
• CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
• Shift Invariance Can Reduce Adversarial Robustness
• Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
• Deep Learning with Label Differential Privacy
• Constraint-Based Regularization of Neural Networks
• Residual Matrix Product State for Machine Learning
• Developing Future Human-Centered Smart Cities: Critical Analysis of Smart City Security, Interpretability, and Ethical Challenges
• Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement
• Quantitative Evaluation of Time-Dependent Multidimensional Projection Techniques
• xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems
• Adaptive Sampling for Minimax Fair Classification
• Learning from a Teacher using Unlabeled Data
• Consistent Representation Learning for High Dimensional Data Analysis
• Data Sanity Check for Deep Learning Systems via Learnt Assertions
• Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
• Constrained Labeling for Weakly Supervised Learning
• A Quantum Edge Detection Algorithm
• Chameleon: Learning Model Initializations Across Tasks With Different Schemas
• Pruned Neural Networks are Surprisingly Modular
• Visual Transformer for Task-aware Active Learning
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment
• A Unified Plug-and-Play Framework for Effective Data Denoising and Robust Abstention
• FLAGS Framework for Comparative Analysis of Federated Learning Algorithms
• Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder
• Deep-learning-based optical image hiding
• A continuum limit for the PageRank algorithm
• Multi-class Generative Adversarial Nets for Semi-supervised Image Classification
• Clusterability in Neural Networks
• Communication-Efficient Federated Learning with Compensated Overlap-FedAvg
• Improving the Robustness of Capsule Networks to Image Affine Transformations
• Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
• Characteristics of Monte Carlo Dropout in Wide Neural Networks
• Self-Paced Learning with Adaptive Deep Visual Embeddings
• AdaSGD: Bridging the gap between SGD and Adam
• Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression
• Deep Neural Architecture Search with Deep Graph Bayesian Optimization
• Federated Learning in Adversarial Settings
• A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
• Large-Scale Subspace Clustering via k-Factorization
• More Than Meets The Eye: Semi-supervised Learning Under Non-IID Data
• InFlow: Robust outlier detection utilizing Normalizing Flows
• Data augmentation in Bayesian neural networks and the cold posterior effect
• FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learning
• Multi-Task Variational Information Bottleneck
• Synaptic metaplasticity with multi-level memristive devices
• Neural Complexity Measures
• Variational Inference with Continuously-Indexed Normalizing Flows
• Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning
• On Stein Variational Neural Network Ensembles
• Post-synaptic potential regularization has potential
• Prediction is very hard, especially about conversion. Predicting user purchases from clickstream data in fashion e-commerce
• Analytic Insights into Structure and Rank of Neural Network Hessian Maps
• Unsupervised Data Imputation via Variational Inference of Deep Subspaces
• Revisiting Deep Neural Network Test Coverage from the Test Effectiveness Perspective
• Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets
• Leveraging tensor kernels to reduce objective function mismatch in deep clustering
• Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
• Gradient descent revisited via an adaptive online learning rate
• Partial local entropy and anisotropy in deep weight spaces
• Differentially Private Deep Learning with Direct Feedback Alignment
• Fuzzy c-Means Clustering for Persistence Diagrams
• Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds
• Using Dimensionality Reduction to Optimize t-SNE
• Machine Learning Method for Functional Assessment of Retinal Models
• Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
• Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation
• Aggregating explanation methods for stable and robust explainability
• LOSSGRAD: automatic learning rate in gradient descent
• QDCNN: Quantum Dilated Convolutional Neural Network
• Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• Wasserstein-Wasserstein Auto-Encoders
• Zero-Shot Deep Domain Adaptation
• McKernel: A Library for Approximate Kernel Expansions in Log-linear Time
• Distribution Estimation to Automate Transformation Policies for Self-Supervision
• Artificial Liver Classifier: A New Alternative to Conventional Machine Learning Models
• Overcoming Catastrophic Forgetting by Generative Regularization
• $\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
• Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learning
• BUZz: BUffer Zones for defending adversarial examples in image classification
• Variational Conditional GAN for Fine-grained Controllable Image Generation
• A Generalizable Approach to Learning Optimizers
• Unbalanced Optimal Transport through Non-negative Penalized Linear Regression
• HypoML: Visual Analysis for Hypothesis-based Evaluation of Machine Learning Models
• Deep Generative Learning via Variational Gradient Flow
• A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
• Deep Contrastive Graph Representation via Adaptive Homotopy Learning
• A Neural Network-Based On-device Learning Anomaly Detector for Edge Devices
• DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
• Edge of chaos as a guiding principle for modern neural network training
• The Impact of Reinitialization on Generalization in Convolutional Neural Networks
• Intra-Ensemble in Neural Networks
• Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis
• Basis Scaling and Double Pruning for Efficient Inference in Network-Based Transfer Learning
• Sequoia: A Software Framework to Unify Continual Learning Research
• Deep Generalized Convolutional Sum-Product Networks
• Privacy-preserving Collaborative Learning with Automatic Transformation Search
• Deep Active Learning with Augmentation-based Consistency Estimation
• Darks and Stripes: Effects of Clothing on Weight Perception
• Efficient Clustering for Stretched Mixtures: Landscape and Optimality
• On Batch Normalisation for Approximate Bayesian Inference
• Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks
• Learning Invariant Representation for Continual Learning
• Overhead MNIST: A Benchmark Satellite Dataset
• Training CNNs with Selective Allocation of Channels
• Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability
• HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
• Adversarial Robustness Guarantees for Gaussian Processes
• Epigenetic evolution of deep convolutional models
• Continual Learning with Fully Probabilistic Models
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Dynamic Sparse Graph for Efficient Deep Learning
• Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
• Orthant Based Proximal Stochastic Gradient Method for ${\ell }_1$-Regularized Optimization
• Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics
• Attention for Image Registration (AiR): an unsupervised Transformer approach
• Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
• Maximizing Information Gain in Partially Observable Environments via Prediction Reward
• Multitask Learning with Single Gradient Step Update for Task Balancing
• MHVAE: a Human-Inspired Deep Hierarchical Generative Model for Multimodal Representation Learning
• Self-Supervised Representation Learning for Visual Anomaly Detection
• Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
• Sparse Spiking Gradient Descent
• Label differential privacy via clustering
• Probabilistic Spatial Transformer Networks
• Topological Insights into Sparse Neural Networks
• URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
• GrCAN: Gradient Boost Convolutional Autoencoder with Neural Decision Forest
• Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
• Finding trainable sparse networks through Neural Tangent Transfer
• A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers
• Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation
• Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification
• Convex Programming Based Spectral Clustering
• Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
• Deep Dimension Reduction for Supervised Representation Learning
• Calibrated simplex-mapping classification
• Approximate Newton-based statistical inference using only stochastic gradients
• Global Convergence of Gradient Descent for Deep Linear Residual Networks
• SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks
• Deep Neural Network Training with Frank-Wolfe
• Bayesian Tensor Network with Polynomial Complexity for Probabilistic Machine Learning
• SimEx: Express Prediction of Inter-dataset Similarity by a Fleet of Autoencoders
• Sliced Iterative Normalizing Flows
• MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
• Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
• Learning Multiclass Classifier Under Noisy Bandit Feedback
• A simple normative network approximates local non-Hebbian learning in the cortex
• Beware the Black-Box: on the Robustness of Recent Defenses to Adversarial Examples
• LSALSA: Accelerated Source Separation via Learned Sparse Coding
• Weakly Supervised Label Learning Flows
• Sparse Quantized Spectral Clustering
• PyTorch-Hebbian: facilitating local learning in a deep learning framework
• Efficient Learning of Generative Models via Finite-Difference Score Matching
• ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problems
• Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
• Federated Learning with Fair Averaging
• Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients
• How Out-of-Distribution Data Hurts Semi-Supervised Learning
• High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve
• Time-multiplexed In-memory computation scheme for mapping Quantized Neural Networks on hybrid CMOS-OxRAM building blocks
• Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach
• Improving the convergence of SGD through adaptive batch sizes
• Reconstruction and Membership Inference Attacks against Generative Models
• Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions
• A Probabilistic Graph Coupling View of Dimension Reduction
• An Effective Hit-or-Miss Layer Favoring Feature Interpretation as Learned Prototypes Deformations
• Path Analysis for Effective Fault Localization in Deep Neural Networks
• Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
• Practical Relative Order Attack in Deep Ranking
• Advances in the training, pruning and enforcement of shape constraints of Morphological Neural Networks using Tropical Algebra
• Learning Translation Invariance in CNNs
• All your loss are belong to Bayes
• A Fully Stochastic Second-Order Trust Region Method
• DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold
• On the Out-of-distribution Generalization of Probabilistic Image Modelling
• Training Generative Adversarial Networks with Adaptive Composite Gradient
• The Connection between Out-of-Distribution Generalization and Privacy of ML Models
• White Noise Analysis of Neural Networks
• Active Generative Adversarial Network for Image Classification
• Uniform Interpolation Constrained Geodesic Learning on Data Manifold
• Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
• k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
• Training on test data: Removing near duplicates in Fashion-MNIST
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
• Provable robustness against all adversarial $l_p$-perturbations for $p\ge 1$
• Convolutional Neural Networks on Randomized Data
• Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces
• Interactive Label Cleaning with Example-based Explanations
• LocoProp: Enhancing BackProp via Local Loss Optimization
• Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
• Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond
• A Review of Formal Methods applied to Machine Learning
• Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
• Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning
• NLNL: Negative Learning for Noisy Labels
• Learning Representations For Images With Hierarchical Labels
• Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks
• Semi-supervised learning by selective training with pseudo labels via confidence estimation
• Heuristic Rank Selection with Progressively Searching Tensor Ring Network
• Rethinking Experience Replay: a Bag of Tricks for Continual Learning
• A PAC-Bayes Analysis of Adversarial Robustness
• QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
• Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification
• Learnable Adaptive Cosine Estimator (LACE) for Image Classification
• Interpretable Visualizations with Differentiating Embedding Networks
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
• Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation
• Network insensitivity to parameter noise via adversarial regularization
• Gradient Descent in RKHS with Importance Labeling
• A new hashing based nearest neighbors selection technique for big datasets
• Feature Selection for Huge Data via Minipatch Learning
• Deep Manifold Transformation for Nonlinear Dimensionality Reduction
• Detecting Memorization in ReLU Networks
• Classify and Generate: Using Classification Latent Space Representations for Image Generations
• STCSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion
• Coupled Gradient Estimators for Discrete Latent Variables
• Effective Evaluation of Deep Active Learning on Image Classification Tasks
• Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators
• Weight-Covariance Alignment for Adversarially Robust Neural Networks
• Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
• PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
• Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
• Pointwise Binary Classification with Pairwise Confidence Comparisons
• Global Semantic Consistency for Zero-Shot Learning
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
• ImagiFilter: A resource to enable the semi-automatic mining of images at scale
• Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units
• Incremental Concept Learning via Online Generative Memory Recall
• A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks
• DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence
• Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
• Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing
• Probabilistic Discriminative Learning with Layered Graphical Models
• Semi-Supervised Class Discovery
• A Multiclass Classification Approach to Label Ranking
• On Positive-Unlabeled Classification in GAN
• Improving the Evaluation of Generative Models with Fuzzy Logic
• TiFL: A Tier-based Federated Learning System
• Convolutional Dictionary Pair Learning Network for Image Representation Learning
• Transfer Learning in General Lensless Imaging through Scattering Media
• Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis
• Mapping the Potential and Pitfalls of "Data Dividends" as a Means of Sharing the Profits of Artificial Intelligence
• Grouping Capsules Based Different Types
• Performance evaluation of an integrated photonic convolutional neural network based on delay buffering and wavelength division multiplexing
• MIM: Mutual Information Machine
• Learning to Remember from a Multi-Task Teacher
• Energy-Inspired Models: Learning with Sampler-Induced Distributions
• Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
• Measuring the Complexity of Domains Used to Evaluate AI Systems
• Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation
• Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding
• On the Robustness of Active Learning
• PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons
• How many winning tickets are there in one DNN?
• Simple, Scalable, and Stable Variational Deep Clustering
• Generative Adversarial Data Programming
• Blind Adversarial Training: Balance Accuracy and Robustness
• Robust Semantic Interpretability: Revisiting Concept Activation Vectors
• Enabling Inference Privacy with Adaptive Noise Injection
• Shapley Explanation Networks
• ExAD: An Ensemble Approach for Explanation-based Adversarial Detection
• Pre-interpolation loss behaviour in neural networks
• Routing Towards Discriminative Power of Class Capsules
• DAC: Deep Autoencoder-based Clustering, a General Deep Learning Framework of Representation Learning
• Gravity Optimizer: a Kinematic Approach on Optimization in Deep Learning
• Selective Forgetting of Deep Networks at a Finer Level than Samples
• On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective
• Generalised Perceptron Learning
• Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
• A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability
• Identifying Incorrect Classifications with Balanced Uncertainty
• Self-Evolutionary Optimization for Pareto Front Learning
• On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization
• Investigating a Baseline Of Self Supervised Learning Towards Reducing Labeling Costs For Image Classification
• DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
• Tutorials on Testing Neural Networks
• Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition
• On Out-of-distribution Detection with Energy-based Models
• Overhead-MNIST: Machine Learning Baselines for Image Classification
• A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
• Asynchronous Distributed Optimization with Redundancy in Cost Functions
• Optimization Variance: Exploring Generalization Properties of DNNs
• Rectangular Flows for Manifold Learning
• On the Evolution of Neuron Communities in a Deep Learning Architecture
• Model-agnostic out-of-distribution detection using combined statistical tests
• On Masked Pre-training and the Marginal Likelihood
• Why is the prediction wrong? Towards underfitting case explanation via meta-classification
• Explaining Black-Box Models through Counterfactuals
• Information Plane Analysis Visualization in Deep Learning via Transfer Entropy
• Uncertainty Quantification From Scaling Laws in Deep Neural Networks
• Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
• Don't Fear Peculiar Activation Functions: EUAF and Beyond
• A distance for mixed-variable and hierarchical domains with meta variables
• Fast gradient-free activation maximization for neurons in spiking neural networks
• Learning via Wasserstein-Based High Probability Generalisation Bounds
• Guiding the retraining of convolutional neural networks against adversarial inputs
• A temporally and spatially local spike-based backpropagation algorithm to enable training in hardware
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• Selective Ensembles for Consistent Predictions
• Lightweight machine unlearning in neural network
• MANDERA: Malicious Node Detection in Federated Learning via Ranking
• EDLaaS: Fully Homomorphic Encryption Over Neural Network Graphs for Vision and Private Strawberry Yield Forecasting
• CVAD: A generic medical anomaly detector based on Cascade VAE
• Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets
• KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
• Clustering with UMAP: Why and How Connectivity Matters
• How many degrees of freedom do we need to train deep networks: a loss landscape perspective
• Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions
• Being a Bit Frequentist Improves Bayesian Neural Networks
• Improved Algorithms for Agnostic Pool-based Active Classification
• Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs
• CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problems
• SGD with Coordinate Sampling: Theory and Practice
• Meta-Learning Bidirectional Update Rules
• Dither computing: a hybrid deterministic-stochastic computing framework
• Implicit Regularization in Tensor Factorization
• Real-Time Decentralized knowledge Transfer at the Edge
• SMG: A Shuffling Gradient-Based Method with Momentum
• Adam with Bandit Sampling for Deep Learning
• Towards Bidirectional Protection in Federated Learning
• Feature Selection Using Batch-Wise Attenuation and Feature Mask Normalization
• Random Polytope Descriptors
• Beneficial Perturbations Network for Defending Adversarial Examples
• Toward Model Parallelism for Deep Neural Network based on Gradient-free ADMM Framework
• Competing AI: How does competition feedback affect machine learning?
• Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem
• Anomaly Detection by Recombining Gated Unsupervised Experts
• Functional Regularization for Representation Learning: A Unified Theoretical Perspective
• Gradient Origin Networks
• Why Attentions May Not Be Interpretable?
• Probably Approximately Correct Constrained Learning
• Provably Robust Metric Learning
• ArchNet: Data Hiding Model in Distributed Machine Learning System
• Controllable Orthogonalization in Training DNNs
• Learning from Aggregate Observations
• Variational Depth Search in ResNets
• Learning a Probabilistic Strategy for Computational Imaging Sensor Selection
• Lifelong Learning with Searchable Extension Units
• Distributed Gradient Methods for Nonconvex Optimization: Local and Global Convergence Guarantees
• Nonlinear classifiers for ranking problems based on kernelized SVM
• Parallel and distributed asynchronous adaptive stochastic gradient methods
• Consistent Batch Normalization for Weighted Loss in Imbalanced-Data Environment
• OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning
• On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Rate-Regularization and Generalization in VAEs
• Learning Permutation Invariant Representations using Memory Networks
• PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
• Biologically-inspired Salience Affected Artificial Neural Network (SANN)
• Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation
• Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift
• An Investigation of Data Poisoning Defenses for Online Learning
• On The Chain Rule Optimal Transport Distance
• Fast Approximate Geodesics for Deep Generative Models
• Closed-Loop Memory GAN for Continual Learning
• Reliable Semi-Supervised Learning when Labels are Missing at Random
• Limited Gradient Descent: Learning With Noisy Labels
• An ETF view of Dropout regularization
• StackNet: Stacking Parameters for Continual learning
• Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss
• On Kernel Method-Based Connectionist Models and Supervised Deep Learning Without Backpropagation
• Do Input Gradients Highlight Discriminative Features?
• Adversarially Robust Kernel Smoothing
• Large-Scale Meta-Learning with Continual Trajectory Shifting
• A statistical framework for efficient out of distribution detection in deep neural networks
• CSIT-Free Model Aggregation for Federated Edge Learning via Reconfigurable Intelligent Surface
• Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
• D3p -- A Python Package for Differentially-Private Probabilistic Programming
• Deep Transformation-Invariant Clustering
• Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
• Gi and Pal Scores: Deep Neural Network Generalization Statistics
• DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing
• Unsupervised Class-Incremental Learning Through Confusion
• Defending Against Adversarial Denial-of-Service Data Poisoning Attacks
• The Compact Support Neural Network
• TensorProjection Layer: A Tensor-Based Dimension Reduction Method in Deep Neural Networks
• Fast Adaptation with Linearized Neural Networks
• Flattening Multiparameter Hierarchical Clustering Functors
• MOOD: Multi-level Out-of-distribution Detection
• Semi-Anchored Multi-Step Gradient Descent Ascent Method for Structured Nonconvex-Nonconcave Composite Minimax Problems
• Mapper Comparison with Wasserstein Metrics
• Photonic Differential Privacy with Direct Feedback Alignment
• On the Robustness of Average Losses for Partial-Label Learning
• Self-Supervised Contextual Bandits in Computer Vision
• HOMRS: High Order Metamorphic Relations Selector for Deep Neural Networks
• Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
• Federated Learning using Smart Contracts on Blockchains, based on Reward Driven Approach
• Sparse Communication via Mixed Distributions
• Anysize GAN: A solution to the image-warping problem
• Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks
• OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary
• Neural Tangent Kernel Empowered Federated Learning
• FedDQ: Communication-Efficient Federated Learning with Descending Quantization
• Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval
• Value-Function-based Sequential Minimization for Bi-level Optimization
• Learning to Be Cautious
• Federated Learning via Plurality Vote
• What augmentations are sensitive to hyper-parameters and why?
• Deformation Robust Roto-Scale-Translation Equivariant CNNs
• Adv-4-Adv: Thwarting Changing Adversarial Perturbations via Adversarial Domain Adaptation
• Defending Adversarial Attacks via Semantic Feature Manipulation
• DIRA: Dynamic Domain Incremental Regularised Adaptation
• Affinity guided Geometric Semi-Supervised Metric Learning
• Spherical Sliced-Wasserstein
• Progressive GANomaly: Anomaly detection with progressively growing GANs
• Efficient CNN with uncorrelated Bag of Features pooling
• AdvJND: Generating Adversarial Examples with Just Noticeable Difference
• VeML: An End-to-End Machine Learning Lifecycle for Large-scale and High-dimensional Data
• Amortised Learning by Wake-Sleep
• The Information Geometry of UMAP
• Adversarial Robustness on Image Classification with $k$-means
• Context-modulation of hippocampal dynamics and deep convolutional networks
• Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
• XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks
• Insights into Ordinal Embedding Algorithms: A Systematic Evaluation
• Unsupervised End-to-End Training with a Self-Defined Target
• Predictive Coding Networks and Inference Learning: Tutorial and Survey
• No Representation without Transformation
• Unsupervised Replay Strategies for Continual Learning with Limited Data
• Robust Partial-Label Learning by Leveraging Class Activation Values
• MaskAAE: Latent space optimization for Adversarial Auto-Encoders
• FW-Shapley: Real-time Estimation of Weighted Shapley Values
• Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data
• Mapping and Scheduling Spiking Neural Networks On Segmented Ladder Bus Architectures
• On Transformations in Stochastic Gradient MCMC
• Developing Convolutional Neural Networks using a Novel Lamarckian Co-Evolutionary Algorithm
• Efficient Multimodal Sampling via Tempered Distribution Flow
• SPENSER: Towards a NeuroEvolutionary Approach for Convolutional Spiking Neural Networks
• Learning to Optimize with Dynamic Mode Decomposition
• Exploring layerwise decision making in DNNs
• Learning Generative Prior with Latent Space Sparsity Constraints
• On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future
• Image anomaly detection with capsule networks and imbalanced datasets
• H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning
• BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
• Top-$k$ Regularization for Supervised Feature Selection
• DPER: Efficient Parameter Estimation for Randomly Missing Data
• MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
• Adaptive Regularization via Residual Smoothing in Deep Learning Optimization
• Recovery Guarantees for Compressible Signals with Adversarial Noise
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• Novel Uncertainty Framework for Deep Learning Ensembles
• Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks
• PatentNet: A Large-Scale Incomplete Multiview, Multimodal, Multilabel Industrial Goods Image Database
• HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
• Learning Set-equivariant Functions with SWARM Mappings
• Revisiting hard thresholding for DNN pruning
• Effects of VLSI Circuit Constraints on Temporal-Coding Multilayer Spiking Neural Networks
• Representation Quality Of Neural Networks Links To Adversarial Attacks and Defences
• Towards Robust Active Feature Acquisition
• Stochastic Generalized Adversarial Label Learning
• eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges
• Reconstructing Images of Two Adjacent Objects through Scattering Medium Using Generative Adversarial Network
• A fast asynchronous MCMC sampler for sparse Bayesian inference
• Ghost Loss to Question the Reliability of Training Data
• Contrastive Learning for Lifted Networks
• Disturbing Target Values for Neural Network Regularization
• Signature-Graph Networks
• Gradient-based Quadratic Multiform Separation
• Instance-Dependent Partial Label Learning
• CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
• Teaching a GAN What Not to Learn
• Self-paced Data Augmentation for Training Neural Networks
• Bilevel Continual Learning
• Towards Interaction Detection Using Topological Analysis on Neural Networks
• LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning
• NeVer 2.0: Learning, Verification and Repair of Deep Neural Networks
• Variation Network: Learning High-level Attributes for Controlled Input Manipulation
• DeepConsensus: using the consensus of features from multiple layers to attain robust image classification
• A Study on the Uncertainty of Convolutional Layers in Deep Neural Networks
• Hierarchical Annotation of Images with Two-Alternative-Forced-Choice Metric Learning
• Student's t-Generative Adversarial Networks
• FedNS: Improving Federated Learning for collaborative image classification on mobile clients
• Experiments with Rich Regime Training for Deep Learning
• Generating Unrestricted Adversarial Examples via Three Parameters
• Set Aggregation Network as a Trainable Pooling Layer
• Tensor Network for Supervised Learning at Finite Temperature
• Learning in Deep Neural Networks Using a Biologically Inspired Optimizer
• Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction
• Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs
• Ordering Dimensions with Nested Dropout Normalizing Flows
• On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
• Effective Version Space Reduction for Convolutional Neural Networks
• Dropout with Tabu Strategy for Regularizing Deep Neural Networks
• Generating Adversarial Examples with an Optimized Quality
• Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• A New Benchmark and Progress Toward Improved Weakly Supervised Learning
• Adma: A Flexible Loss Function for Neural Networks
• Bayesian Counterfactual Risk Minimization
• On the Intrinsic Differential Privacy of Bagging
• iCVI-ARTMAP: Accelerating and improving clustering using adaptive resonance theory predictive mapping and incremental cluster validity indices
• Channel-Directed Gradients for Optimization of Convolutional Neural Networks
• Topological Data Analysis of Decision Boundaries with Application to Model Selection
• ALEX: Active Learning based Enhancement of a Model's Explainability
• Adversarial Learning for Zero-shot Domain Adaptation
• Optimal Transport Based Generative Autoencoders
• Mapper Based Classifier
• Multi-level Similarity Learning for Low-Shot Recognition
• Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation
• Angular Learning: Toward Discriminative Embedded Features
• DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
• Improving compute efficacy frontiers with SliceOut
• Single-Photon Image Classification
• PAC${}^m$-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime
• MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
• Content-Adaptive Pixel Discretization to Improve Model Robustness
• Effect of the initial configuration of weights on the training and function of artificial neural networks
• Generalized Doubly Reparameterized Gradient Estimators
• Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
• On the detection of Out-Of-Distribution samples in Multiple Instance Learning
• Explicit Gradient Learning
• Shape Defense Against Adversarial Attacks
• Is the U-Net Directional-Relationship Aware?
• An Integrated Approach to Produce Robust Models with High Efficiency
• Training Generative Networks with general Optimal Transport distances
• An Adaptive Empirical Bayesian Method for Sparse Deep Learning
• Target Propagation via Regularized Inversion
• A Geometric Approach to Online Streaming Feature Selection
• Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structure
• DNNs as Layers of Cooperating Classifiers
• Practical Insights of Repairing Model Problems on Image Classification
• Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
• Shared and Private VAEs with Generative Replay for Continual Learning
• Part-based approximations for morphological operators using asymmetric auto-encoders
• $\rho$-VAE: Autoregressive parametrization of the VAE encoder
• Measuring Information Transfer in Neural Networks
• Increasing the Generalisation Capacity of Conditional VAEs
• Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection
• Simple and Scalable Parallelized Bayesian Optimization
• Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees
• Targeted Deep Learning: Framework, Methods, and Applications
• HAD-GAN: A Human-perception Auxiliary Defense GAN to Defend Adversarial Examples
• The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches
• Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior
• Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders
• RSAC: Regularized Subspace Approximation Classifier for Lightweight Continuous Learning
• Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks
• Auto-CASH: Autonomous Classification Algorithm Selection with Deep Q-Network
• Group Equivariant Subsampling
• An Ensemble Approach Towards Adversarial Robustness
• Atlas Based Representation and Metric Learning on Manifolds
• Learning Digital Circuits: A Journey Through Weight Invariant Self-Pruning Neural Networks
• Towards Robust Classification with Deep Generative Forests
• Non-Gradient Manifold Neural Network
• Weight Friction: A Simple Method to Overcome Catastrophic Forgetting and Enable Continual Learning
• Nested Learning For Multi-Granular Tasks
• Adaptive Weight Decay for Deep Neural Networks
• Invertible Manifold Learning for Dimension Reduction
• Robust Unsupervised Multi-Object Tracking in Noisy Environments
• BooVAE: Boosting Approach for Continual Learning of VAE
• A Framework to Learn with Interpretation
• A general framework for defining and optimizing robustness
• Novelty Detection via Contrastive Learning with Negative Data Augmentation
• Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays
• Visualizing the Finer Cluster Structure of Large-Scale and High-Dimensional Data
• Efficient Tensor Contraction via Fast Count Sketch
• Coded-InvNet for Resilient Prediction Serving Systems
• MTL2L: A Context Aware Neural Optimiser
• Bounded Expectation of Label Assignment: Dataset Annotation by Supervised Splitting with Bias-Reduction Techniques
• MCMC-Interactive Variational Inference
• From Boltzmann Machines to Neural Networks and Back Again
• Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence
• Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN
• How many samples are needed to reliably approximate the best linear estimator for a linear inverse problem?
• Variance Regularization for Accelerating Stochastic Optimization
• Exact and Consistent Interpretation of Piecewise Linear Models Hidden behind APIs: A Closed Form Solution
• CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification
• Cluster Representatives Selection in Non-Metric Spaces for Nearest Prototype Classification
• Investigating the Effect of Intraclass Variability in Temporal Ensembling
• Probabilistic Decoupling of Labels in Classification
• Lifelong Mixture of Variational Autoencoders
• Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer
• Nonlinear Least Squares for Large-Scale Machine Learning using Stochastic Jacobian Estimates
• Continual learning using hash-routed convolutional neural networks
• Deep Image Feature Learning with Fuzzy Rules
• Leave-one-out Unfairness
• Likelihood Landscapes: A Unifying Principle Behind Many Adversarial Defenses
• Inferring Hierarchical Mixture Structures: A Bayesian Nonparametric Approach
• Pruning-Aware Merging for Efficient Multitask Inference
• On Addressing Heterogeneity in Federated Learning for Autonomous Vehicles Connected to a Drone Orchestrator
• EIS -- a family of activation functions combining Exponential, ISRU, and Softplus
• Efficient Byzantine-Resilient Stochastic Gradient Desce
• Towards More Efficient Federated Learning with Better Optimization Objects
• Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding
• A Trainable Multiplication Layer for Auto-correlation and Co-occurrence Extraction
• ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results
• CrossedWires: A Dataset of Syntactically Equivalent but Semantically Disparate Deep Learning Models
• Using Topological Framework for the Design of Activation Function and Model Pruning in Deep Neural Networks
• GANs for learning from very high class conditional noisy labels
• Automated Robustness with Adversarial Training as a Post-Processing Step
• Task Guided Compositional Representation Learning for ZDA
• Mitigating Sampling Bias and Improving Robustness in Active Learning
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• TableNet: a multiplier-less implementation of neural networks for inferencing
• A novel network training approach for open set image recognition
• DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
• Multi-class Probabilistic Bounds for Self-learning
• Generative Adversarial Networks with Inverse Transformation Unit
• Bottom-up Hierarchical Classification Using Confusion-based Logit Compression
• Generalizing Neural Networks by Reflecting Deviating Data in Production
• L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set
• The Neglected Sibling: Isotropic Gaussian Posterior for VAE
• PR Product: A Substitute for Inner Product in Neural Networks
• Does the Layout Really Matter? A Study on Visual Model Accuracy Estimation
• Dendritic Self-Organizing Maps for Continual Learning
• Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning
• Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning
• A Closer Look at Reference Learning for Fourier Phase Retrieval
• Towards Sharper First-Order Adversary with Quantized Gradients
• Loosely Coupled Federated Learning Over Generative Models
• Facilitate the Parametric Dimension Reduction by Gradient Clipping
• How to boost autoencoders?
• Rethinking Neural Networks With Benford's Law
• Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• PipeTune: Pipeline Parallelism of Hyper and System Parameters Tuning for Deep Learning Clusters
• Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise
• A Non-Intrusive Correction Algorithm for Classification Problems with Corrupted Data
• Understanding Classifier Mistakes with Generative Models
• Differentiable Segmentation of Sequences
• Over-parametrized neural networks as under-determined linear systems
• Unintended Effects on Adaptive Learning Rate for Training Neural Network with Output Scale Change
• On the generalization of bayesian deep nets for multi-class classification
• Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
• Learning from Incomplete Features by Simultaneous Training of Neural Networks and Sparse Coding
• A $0.11-0.38$ pJ/cycle Differential Ring Oscillator in $65$ nm CMOS for Robust Neurocomputing
• A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions
• Evolving parametrized Loss for Image Classification Learning on Small Datasets
• Detecting Deep Neural Network Defects with Data Flow Analysis
• Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
• Autoequivariant Network Search via Group Decomposition
• Regularizing Neural Networks via Stochastic Branch Layers
• Network-Density-Controlled Decentralized Parallel Stochastic Gradient Descent in Wireless Systems
• Robust Trust Region for Weakly Supervised Segmentation
• A Makefile for Developing Containerized LaTeX Technical Documents
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• High Mutual Information in Representation Learning with Symmetric Variational Inference
• Low-Regret Active learning
• Iterative Alignment Flows
• Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system
• Improve SGD Training via Aligning Mini-batches
• Efficient Data-Dependent Learnability
• Spatially Correlated Patterns in Adversarial Images
• A Simple Framework to Quantify Different Types of Uncertainty in Deep Neural Networks for Image Classification
• Deep Learning in Target Space
• FILTRA: Rethinking Steerable CNN by Filter Transform
• Stochastic Computing for Hardware Implementation of Binarized Neural Networks
• Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures
• Efficient Algorithms for Constructing an Interpolative Decomposition
• An Efficient Agreement Mechanism in CapsNets By Pairwise Product
• Greedy Bayesian Posterior Approximation with Deep Ensembles
• TAG: Task-based Accumulated Gradients for Lifelong learning
• Data Augmentation with Variational Autoencoders and Manifold Sampling
• mil-benchmarks: Standardized Evaluation of Deep Multiple-Instance Learning Techniques
• Learning a Deep Generative Model like a Program: the Free Category Prior
• In-Hardware Learning of Multilayer Spiking Neural Networks on a Neuromorphic Processor
• Sparsity-Probe: Analysis tool for Deep Learning Models
• Evidential Turing Processes
• Stein Latent Optimization for Generative Adversarial Networks
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning
• Detecting Learning vs Memorization in Deep Neural Networks using Shared Structure Validation Sets
• GIM: Gaussian Isolation Machines
• ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense
• Stochastic Doubly Robust Gradient
• Pixel-wise Conditioning of Generative Adversarial Networks
• About contrastive unsupervised representation learning for classification and its convergence
• Hierarchical Models: Intrinsic Separability in High Dimensions
• TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion
• Learning Identity-Preserving Transformations on Data Manifolds
• Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning
• FoCL: Feature-Oriented Continual Learning for Generative Models
• Input Invex Neural Network
• Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework
• Soft Compression for Lossless Image Coding
• Feedback Control for Online Training of Neural Networks
• Cascade Decoders-Based Autoencoders for Image Reconstruction
• Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning Models
• Structured Stochastic Gradient MCMC
• Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks
• Open-World Class Discovery with Kernel Networks
• Implicit Generative Copulas
• Interpretable BoW Networks for Adversarial Example Detection
• Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection
• Entropic Issues in Likelihood-Based OOD Detection
• Genealogical Population-Based Training for Hyperparameter Optimization
• Incremental Verification of Fixed-Point Implementations of Neural Networks
• Cross-Domain Latent Modulation for Variational Transfer Learning
• Corella: A Private Multi Server Learning Approach based on Correlated Queries
• Architectural Resilience to Foreground-and-Background Adversarial Noise
• SimpleBooks: Long-term dependency book dataset with simplified English vocabulary for word-level language modeling
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Learning Deep Representation with Energy-Based Self-Expressiveness for Subspace Clustering
• Scalable Deep $k$-Subspace Clustering
• Quadratic Multiform Separation: A New Classification Model in Machine Learning
• Magnitude and Uncertainty Pruning Criterion for Neural Networks
• Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models
• Stochastic Sparse Learning with Momentum Adaptation for Imprecise Memristor Networks
• Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
• Incremental Class Learning using Variational Autoencoders with Similarity Learning
• Virtual Conditional Generative Adversarial Networks
• Combining Differential Privacy and Byzantine Resilience in Distributed SGD
• GenURL: A General Framework for Unsupervised Representation Learning
• The duality structure gradient descent algorithm: analysis and applications to neural networks
• Condensed Composite Memory Continual Learning
• Lossless Compression with Probabilistic Circuits
• CheckNet: Secure Inference on Untrusted Devices
• Complementary Ensemble Learning
• Nonlinear Tensor Ring Network
• Large-data determinantal clustering
• Trust the Critics: Generatorless and Multipurpose WGANs with Initial Convergence Guarantees
• Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection
• Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization
• Capsule Networks Do Not Need to Model Everything
• Local Convergence of Adaptive Gradient Descent Optimizers
• Variational Laplace for Bayesian neural networks
• Skeptical Deep Learning with Distribution Correction
• Self-Checking Deep Neural Networks in Deployment
• Vanishing Twin GAN: How training a weak Generative Adversarial Network can improve semi-supervised image classification
• Dynamic Flows on Curved Space Generated by Labeled Data
• Learning Inward Scaled Hypersphere Embedding: Exploring Projections in Higher Dimensions
• PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search
• Exact Stochastic Second Order Deep Learning
• MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Deep Neural Networks
• Dropout Drops Double Descent
• Spatially-Coupled Neural Network Architectures
• Understanding Interpretability by generalized distillation in Supervised Classification
• Widely Linear Kernels for Complex-Valued Kernel Activation Functions
• Towards glass-box CNNs
• ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms
• Prior-Independent Auctions for the Demand Side of Federated Learning
• Distributed Collapsed Gibbs Sampler for Dirichlet Process Mixture Models in Federated Learning
• Disentanglement based Active Learning
• Characterizing and Measuring the Similarity of Neural Networks with Persistent Homology
• Disassembling Object Representations without Labels
• Learning Spatial Relationships between Samples of Patent Image Shapes
• Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
• Stochastic gradient algorithms from ODE splitting perspective
• Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems
• A One-step Approach to Covariate Shift Adaptation
• Does the Adam Optimizer Exacerbate Catastrophic Forgetting?
• Controlled privacy leakage propagation throughout overlapping grouped learning
• Clusters in Explanation Space: Inferring disease subtypes from model explanations
• Cognitive Consistency Routing Algorithm of Capsule-network
• Sparsely Activated Networks: A new method for decomposing and compressing data
• On Intrinsic Dataset Properties for Adversarial Machine Learning
• Consensus Driven Learning
• DaiMoN: A Decentralized Artificial Intelligence Model Network
• Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
• A Discriminative Gaussian Mixture Model with Sparsity
• neuralRank: Searching and ranking ANN-based model repositories
• DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy
• Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems
• Neural Additive and Basis Models with Feature Selection and Interactions
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
• Generating Adversarial Examples With Conditional Generative Adversarial Net
• Neural Network Training with Approximate Logarithmic Computations
• Supervised Encoding for Discrete Representation Learning
• One-Shot Clustering for Federated Learning
• Learning to Utilize Correlated Auxiliary Noise: A Possible Quantum Advantage
• Toward a Realistic Benchmark for Out-of-Distribution Detection