Overcoming catastrophic forgetting in neural networks

Abstract

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks which they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on the MNIST hand written digit dataset and by learning several Atari 2600 games sequentially.

References in corpus (7)

• Progressive Neural Networks
• The Arcade Learning Environment: An Evaluation Platform for General Agents
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
• Revisiting Natural Gradient for Deep Networks
• Synaptic sampling: A connection between PSP variability and uncertainty explains neurophysiological observations
• Computational principles of biological memory

Cited by in corpus (1034)

• On the Opportunities and Risks of Foundation Models
• A continual learning survey: Defying forgetting in classification tasks
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• Towards Personalized Federated Learning
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• How To Backdoor Federated Learning
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Deep Reinforcement Learning: An Overview
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• A Survey on Anomaly Detection for Technical Systems using LSTM Networks
• Physical reservoir computing -- An introductory perspective
• Artificial neural networks for neuroscientists: A primer
• Precision Health Data: Requirements, Challenges and Existing Techniques for Data Security and Privacy
• Experience Replay for Continual Learning
• The Natural Language Decathlon: Multitask Learning as Question Answering
• On Data Augmentation for GAN Training
• On Tiny Episodic Memories in Continual Learning
• FearNet: Brain-Inspired Model for Incremental Learning
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Class-Incremental Learning: A Survey
• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Continual Learning of Context-dependent Processing in Neural Networks
• Overcoming catastrophic forgetting with hard attention to the task
• Ditto: Fair and Robust Federated Learning Through Personalization
• Encoder Based Lifelong Learning
• On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
• Go-Explore: a New Approach for Hard-Exploration Problems
• Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
• Rapid online learning and robust recall in a neuromorphic olfactory circuit
• Continual Learning with Deep Generative Replay
• Generative replay with feedback connections as a general strategy for continual learning
• Lifelong Learning with Dynamically Expandable Networks
• Towards Robust Evaluations of Continual Learning
• Adaptive Extreme Edge Computing for Wearable Devices
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Learned Cardinalities: Estimating Correlated Joins with Deep Learning
• Learning and Evaluating General Linguistic Intelligence
• Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• Parameter-Efficient Transfer Learning for NLP
• Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions
• Overcoming Forgetting in Federated Learning on Non-IID Data
• K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
• Compacting, Picking and Growing for Unforgetting Continual Learning
• Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
• Decentralized Federated Learning via Mutual Knowledge Transfer
• Class-Incremental Continual Learning into the eXtended DER-verse
• Digital Watermarking for Deep Neural Networks
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• Reliable extrapolation of deep neural operators informed by physics or sparse observations
• Deep Generative Dual Memory Network for Continual Learning
• Practical Deep Learning with Bayesian Principles
• Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
• Intelligence at the Extreme Edge: A Survey on Reformable TinyML
• Variational Federated Multi-Task Learning
• Federated Continual Learning via Knowledge Fusion: A Survey
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
• SuperAnimal pretrained pose estimation models for behavioral analysis
• LAMOL: LAnguage MOdeling for Lifelong Language Learning
• Lifelong Generative Modeling
• OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models
• On Quadratic Penalties in Elastic Weight Consolidation
• Incremental Object Detection via Meta-Learning
• Toward an AI Physicist for Unsupervised Learning
• Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
• What Are Bayesian Neural Network Posteriors Really Like?
• Machine Learning for Orders of Magnitude Speedup in Multi-Objective Optimization of Particle Accelerator Systems
• Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
• Machine learning with neural networks
• Implicit Generation and Generalization in Energy-Based Models
• On the Creativity of Large Language Models
• A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
• Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization
• Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments
• Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
• DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks
• 6G White Paper on Machine Learning in Wireless Communication Networks
• Streaming Graph Neural Networks via Continual Learning
• Generalization and Regularization in DQN
• Incremental Classifier Learning with Generative Adversarial Networks
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
• A survey on intrinsic motivation in reinforcement learning
• Dark Experience for General Continual Learning: a Strong, Simple Baseline
• Machine Learning for Condensed Matter Physics
• Continual Learning via Neural Pruning
• Understanding the Role of Training Regimes in Continual Learning
• PyCIL: A Python Toolbox for Class-Incremental Learning
• Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
• Functional Regularisation for Continual Learning with Gaussian Processes
• Coresets via Bilevel Optimization for Continual Learning and Streaming
• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
• Demonstration of Decentralized, Physics-Driven Learning
• A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
• Cluster-Level Contrastive Learning for Emotion Recognition in Conversations
• Construction of Knowledge Graphs: State and Challenges
• Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
• Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
• Graph Neural Networks with Continual Learning for Fake News Detection from Social Media
• Synaptic metaplasticity in binarized neural networks
• Online Continual Learning with Maximally Interfered Retrieval
• GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems
• Selfless Sequential Learning
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• How to Retrain Recommender System? A Sequential Meta-Learning Method
• Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks
• Few-Shot Learning with Geometric Constraints
• Continual Local Training for Better Initialization of Federated Models
• Task Agnostic Continual Learning Using Online Variational Bayes
• Learning to Continually Learn
• REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data
• Salvaging Federated Learning by Local Adaptation
• Continual Learning for Predictive Maintenance: Overview and Challenges
• Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis
• Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts
• SpaceNet: Make Free Space For Continual Learning
• Lifelong Incremental Reinforcement Learning with Online Bayesian Inference
• Lifelong Teacher-Student Network Learning
• KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction
• Critical Learning Periods in Deep Neural Networks
• Memory Replay GANs: learning to generate images from new categories without forgetting
• DualNet: Continual Learning, Fast and Slow
• Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
• What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• A Bayesian Federated Learning Framework with Online Laplace Approximation
• Task Agnostic Continual Learning via Meta Learning
• Continual Deep Learning by Functional Regularisation of Memorable Past
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
• Triple Memory Networks: a Brain-Inspired Method for Continual Learning
• Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
• Adaptive Online Incremental Learning for Evolving Data Streams
• Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?
• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
• Adversarial Examples in Modern Machine Learning: A Review
• AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning
• What shapes feature representations? Exploring datasets, architectures, and training
• SATS: Self-Attention Transfer for Continual Semantic Segmentation
• A reinforcement learning approach to rare trajectory sampling
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• Prototype-Guided Memory Replay for Continual Learning
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
• A Unifying Bayesian View of Continual Learning
• Efficient Continual Learning in Neural Networks with Embedding Regularization
• Cognitively-Inspired Model for Incremental Learning Using a Few Examples
• CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
• Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
• A neural network walks into a lab: towards using deep nets as models for human behavior
• Superposition of many models into one
• Continual Learning on Dynamic Graphs via Parameter Isolation
• Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach
• Metabolic constraints on synaptic learning and memory
• Continual Learning and Catastrophic Forgetting
• Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
• Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning
• Sequence Length is a Domain: Length-based Overfitting in Transformer Models
• Modifying Memories in Transformer Models
• CLeaR: An Adaptive Continual Learning Framework for Regression Tasks
• A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application
• Subspace Regularizers for Few-Shot Class Incremental Learning
• DER: Dynamically Expandable Representation for Class Incremental Learning
• M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• A Strategy for an Uncompromising Incremental Learner
• Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks
• Learning Abstract Options
• Towards Continual Knowledge Learning of Language Models
• Online Coreset Selection for Rehearsal-based Continual Learning
• Learning without Forgetting for Vision-Language Models
• Orthogonal Gradient Descent for Continual Learning
• Learning offline: memory replay in biological and artificial reinforcement learning
• Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
• Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
• WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
• Continual Learning for Generative Retrieval over Dynamic Corpora
• Continual Semi-Supervised Learning through Contrastive Interpolation Consistency
• Budget-Aware Adapters for Multi-Domain Learning
• Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights
• Multimodal Parameter-Efficient Few-Shot Class Incremental Learning
• Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks
• Continual Learning for Fake Audio Detection
• Online Continual Learning on Sequences
• DisCoRL: Continual Reinforcement Learning via Policy Distillation
• Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
• La-MAML: Look-ahead Meta Learning for Continual Learning
• LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
• Multi-Task Incremental Learning for Object Detection
• Depthwise Convolution is All You Need for Learning Multiple Visual Domains
• Class-incremental Learning with Pre-allocated Fixed Classifiers
• A distillation-based approach integrating continual learning and federated learning for pervasive services
• End-to-End Incremental Learning
• Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset
• An Investigation of Replay-based Approaches for Continual Learning
• QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
• Domain-incremental Cardiac Image Segmentation with Style-oriented Replay and Domain-sensitive Feature Whitening
• Toward Understanding Catastrophic Forgetting in Continual Learning
• Been There, Done That: Meta-Learning with Episodic Recall
• CPR: Classifier-Projection Regularization for Continual Learning
• On the Decision Boundary of Deep Neural Networks
• Federated Continual Learning with Weighted Inter-client Transfer
• Federated Continual Learning: Concepts, Challenges, and Solutions
• Incremental Few-Shot Learning with Attention Attractor Networks
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
• Improving and Understanding Variational Continual Learning
• ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
• Visual pathways from the perspective of cost functions and multi-task deep neural networks
• Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay
• Continual Learning with Gated Incremental Memories for sequential data processing
• Open World Object Detection: A Survey
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Multi-Granularity Regularized Re-Balancing for Class Incremental Learning
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review
• Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• Continual Learning with Adaptive Weights (CLAW)
• Defining Benchmarks for Continual Few-Shot Learning
• Improved Schemes for Episodic Memory-based Lifelong Learning
• Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning
• Gradient Projection Memory for Continual Learning
• Meta-Consolidation for Continual Learning
• Laplace Redux -- Effortless Bayesian Deep Learning
• Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
• SupportNet: solving catastrophic forgetting in class incremental learning with support data
• Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data
• Deep Reinforcement Learning Methods for Structure-Guided Processing Path Optimization
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity
• Incremental Deep Neural Network Learning using Classification Confidence Thresholding
• Toward Continual Learning for Conversational Agents
• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• Uncertainty-guided Continual Learning with Bayesian Neural Networks
• Direction Concentration Learning: Enhancing Congruency in Machine Learning
• Meta Continual Learning
• EEC: Learning to Encode and Regenerate Images for Continual Learning
• A Theory of Relation Learning and Cross-domain Generalization
• Continual Learning via Inter-Task Synaptic Mapping
• Mind the Gap: Assessing Temporal Generalization in Neural Language Models
• Learned multi-stability in mechanical networks
• Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
• Multi-task Deep Reinforcement Learning with PopArt
• Universal Successor Features Approximators
• Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty
• Uncertainty-based Modulation for Lifelong Learning
• Human-like generalization in a machine through predicate learning
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Parameter-Efficient Transfer Learning with Diff Pruning
• Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
• AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets
• Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
• On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
• Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
• AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications
• Continual Reinforcement Learning with Complex Synapses
• Replay in Deep Learning: Current Approaches and Missing Biological Elements
• Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets
• Catastrophic forgetting: still a problem for DNNs
• REMIND Your Neural Network to Prevent Catastrophic Forgetting
• Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors
• Active and Incremental Learning with Weak Supervision
• Continual learning of longitudinal health records
• EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
• Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
• GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning
• Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation
• The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
• Elastic Weight Consolidation (EWC): Nuts and Bolts
• Anomaly Detection with Score Distribution Discrimination
• Multi-View Class Incremental Learning
• Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation
• Design of intentional backdoors in sequential models
• Few-Shot Incremental Learning with Continually Evolved Classifiers
• Continuous learning of spiking networks trained with local rules
• Continuous fake media detection: adapting deepfake detectors to new generative techniques
• Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision
• Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling
• Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning
• Regularization Shortcomings for Continual Learning
• On The Impact of Machine Learning Randomness on Group Fairness
• AirLoop: Lifelong Loop Closure Detection
• Contrastive Syn-to-Real Generalization
• Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation
• Beneficial Perturbation Network for designing general adaptive artificial intelligence systems
• The Effectiveness of Memory Replay in Large Scale Continual Learning
• Personalized Federated Deep Learning for Pain Estimation From Face Images
• Online Lifelong Generalized Zero-Shot Learning
• Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
• Rainbow Memory: Continual Learning with a Memory of Diverse Samples
• Learning credit assignment
• Progressive Memory Banks for Incremental Domain Adaptation
• Learning Representations for New Sound Classes With Continual Self-Supervised Learning
• Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods
• Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
• CCL: Continual Contrastive Learning for LiDAR Place Recognition
• Removing Backdoor-Based Watermarks in Neural Networks with Limited Data
• An Adaptive Random Path Selection Approach for Incremental Learning
• Scalable and Order-robust Continual Learning with Additive Parameter Decomposition
• LCA: Loss Change Allocation for Neural Network Training
• Strategies for Using Proximal Policy Optimization in Mobile Puzzle Games
• Wandering Within a World: Online Contextualized Few-Shot Learning
• Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
• Optimal pre-train/fine-tune strategies for accurate material property predictions
• On the Optimal Weighted ${\ell }_2$ Regularization in Overparameterized Linear Regression
• New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning
• The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
• Measuring and regularizing networks in function space
• Continual Prune-and-Select: Class-incremental learning with specialized subnetworks
• Continuum: Simple Management of Complex Continual Learning Scenarios
• Continual Classification Learning Using Generative Models
• Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning
• Two-Level Residual Distillation based Triple Network for Incremental Object Detection
• Distilling Causal Effect of Data in Class-Incremental Learning
• Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks
• Adversarial training in communication constrained federated learning
• Exploring Benefits of Transfer Learning in Neural Machine Translation
• Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
• Robust Neural Machine Translation for Clean and Noisy Speech Transcripts
• One Person, One Model, One World: Learning Continual User Representation without Forgetting
• Towards Training Recurrent Neural Networks for Lifelong Learning
• Meta-Learning with Sparse Experience Replay for Lifelong Language Learning
• Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification
• Few-shot Image Generation via Cross-domain Correspondence
• Few-Shot Class-Incremental Learning
• Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning
• Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
• Robust Conversational AI with Grounded Text Generation
• Batch-level Experience Replay with Review for Continual Learning
• Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
• Generalized Variational Continual Learning
• Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance
• Semantic Drift Compensation for Class-Incremental Learning
• A Neural Span-Based Continual Named Entity Recognition Model
• Online Class-Incremental Continual Learning with Adversarial Shapley Value
• Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
• Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties
• Class Gradient Projection For Continual Learning
• EEG-based performance-driven adaptive automated hazard alerting system in security surveillance support
• GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
• Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task
• Federated Gaussian Process: Convergence, Automatic Personalization and Multi-fidelity Modeling
• Improving Sequential Recommendations with LLMs
• Continual Learning in Neural Networks
• Continual Learning for Domain Adaptation in Chest X-ray Classification
• Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
• ACE: Adapting to Changing Environments for Semantic Segmentation
• DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics
• Learning from Data Streams: An Overview and Update
• Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
• Empowering Bayesian Neural Networks with Functional Priors through Anchored Ensembling for Mechanics Surrogate Modeling Applications
• Deep learning via message passing algorithms based on belief propagation
• Continual Learning in Recurrent Neural Networks
• Few-Shot Self Reminder to Overcome Catastrophic Forgetting
• A multifidelity approach to continual learning for physical systems
• Personalized Federated Continual Learning via Multi-granularity Prompt
• Towards Understanding the Transferability of Deep Representations
• MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment
• CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision
• Continual Learning on the Edge with TensorFlow Lite
• Ctrl-Z: Recovering from Instability in Reinforcement Learning
• Self-Attentional Credit Assignment for Transfer in Reinforcement Learning
• Neural Polysynthetic Language Modelling
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
• Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness
• Estimating Model Uncertainty of Neural Networks in Sparse Information Form
• ConDA: Continual Unsupervised Domain Adaptation
• Group privacy for personalized federated learning
• Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
• Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
• Artificial intelligence for online characterization of ultrashort X-ray free-electron laser pulses
• Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis
• Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning
• FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
• A Framework of Transfer Learning in Object Detection for Embedded Systems
• Combining pre-trained language models and structured knowledge
• Linear Mode Connectivity in Multitask and Continual Learning
• Accelerating Algebraic Multigrid Methods via Artificial Neural Networks
• Towards continuous learning for glioma segmentation with elastic weight consolidation
• Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
• Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines
• Parameter-Efficient Abstractive Question Answering over Tables or Text
• Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Review
• Reconciling meta-learning and continual learning with online mixtures of tasks
• Sentence Embedding Alignment for Lifelong Relation Extraction
• Analyzing Knowledge Transfer in Deep Q-Networks for Autonomously Handling Multiple Intersections
• Bayesian Deep Learning via Subnetwork Inference
• Lifelong Learning of Compositional Structures
• Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
• Leveraging Old Knowledge to Continually Learn New Classes in Medical Images
• AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization
• Example Forgetting: A Novel Approach to Explain and Interpret Deep Neural Networks in Seismic Interpretation
• Reset-Free Lifelong Learning with Skill-Space Planning
• Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
• Distillation Techniques for Pseudo-rehearsal Based Incremental Learning
• Continual Human-in-the-Loop Optimization
• Can Synthetic Faces Undo the Damage of Dataset Bias to Face Recognition and Facial Landmark Detection?
• Balancing Reinforcement Learning Training Experiences in Interactive Information Retrieval
• Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
• Emergent Communication Pretraining for Few-Shot Machine Translation
• Task Relation-aware Continual User Representation Learning
• Continual BERT: Continual Learning for Adaptive Extractive Summarization of COVID-19 Literature
• Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
• Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence
• Routing Networks with Co-training for Continual Learning
• Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
• Generative Feature Replay For Class-Incremental Learning
• Training Networks in Null Space of Feature Covariance for Continual Learning
• Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
• Generalized Continual Zero-Shot Learning
• Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
• Online Deep Learning based on Auto-Encoder
• Explaining Deep Models through Forgettable Learning Dynamics
• DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
• Eight challenges in developing theory of intelligence
• Machine Learning-based models in particle-in-cell codes for advanced physics extensions
• Unified Question Generation with Continual Lifelong Learning
• Continual Learning for Monolingual End-to-End Automatic Speech Recognition
• SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
• Encoders and Ensembles for Task-Free Continual Learning
• Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning
• Generative Replay-based Continual Zero-Shot Learning
• Finite Meta-Dynamic Neurons in Spiking Neural Networks for Spatio-temporal Learning
• Prediction error-driven memory consolidation for continual learning. On the case of adaptive greenhouse models
• Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
• Incremental Learning In Online Scenario
• Blessing of dimensionality at the edge
• Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
• On the role of neurogenesis in overcoming catastrophic forgetting
• Non-Iterative Knowledge Fusion in Deep Convolutional Neural Networks
• Uncertainty in Multitask Transfer Learning
• Keep and Learn: Continual Learning by Constraining the Latent Space for Knowledge Preservation in Neural Networks
• Software engineering and the SP Theory of Intelligence
• On the Exploration of Incremental Learning for Fine-grained Image Retrieval
• Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy
• On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
• Design Space of Behaviour Planning for Autonomous Driving
• A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
• Learning Portable Representations for High-Level Planning
• Advancing Italian Biomedical Information Extraction with Transformers-based Models: Methodological Insights and Multicenter Practical Application
• Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation
• On Class Orderings for Incremental Learning
• Continual Reinforcement Learning with Multi-Timescale Replay
• Rethinking Knowledge Distillation in Collaborative Machine Learning: Memory, Knowledge, and Their Interactions
• A Continual Learning Framework for Adaptive Defect Classification and Inspection
• Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
• Lifelong Graph Learning
• Pathological spectra of the Fisher information metric and its variants in deep neural networks
• Large Multimodal Models for Low-Resource Languages: A Survey
• Continuous Meta-Learning without Tasks
• A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition
• Gradient Episodic Memory with a Soft Constraint for Continual Learning
• Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
• Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation
• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
• Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification
• Statistical mechanics of continual learning: variational principle and mean-field potential
• Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models
• Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft
• Imbalanced Continual Learning with Partitioning Reservoir Sampling
• Learning Adaptive Embedding Considering Incremental Class
• CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents
• Consistent Video Depth Estimation
• A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures
• Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
• ARCADe: A Rapid Continual Anomaly Detector
• Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks
• Editable Neural Networks
• A Lifelong Learning Approach to Mobile Robot Navigation
• A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption
• Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning
• Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks
• Continual Domain-Tuning for Pretrained Language Models
• Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• Self-Supervised Learning Aided Class-Incremental Lifelong Learning
• Supermasks in Superposition
• Class Balance Matters to Active Class-Incremental Learning
• Memory Efficient Experience Replay for Streaming Learning
• Quantum continual learning on a programmable superconducting processor
• Federated Learning on Non-IID Data: A Survey
• An Analytical Theory of Curriculum Learning in Teacher-Student Networks
• Learning latent representations across multiple data domains using Lifelong VAEGAN
• Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization
• Autoencoder-Based Incremental Class Learning without Retraining on Old Data
• Human Motion Prediction via Continual Prior Compensation
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
• The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning
• Online Structured Meta-learning
• Latent Spectral Regularization for Continual Learning
• Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Exploring the Intersection between Neural Architecture Search and Continual Learning
• A Tailored Pre-Training Model for Task-Oriented Dialog Generation
• Meta-learnt priors slow down catastrophic forgetting in neural networks
• If deep learning is the answer, then what is the question?
• Modular Meta-Learning with Shrinkage
• AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning
• Investigating Multilingual NMT Representations at Scale
• Adaptive Online Planning for Continual Lifelong Learning
• Teaching Multiple Concepts to a Forgetful Learner
• Continual Graph Learning: A Survey
• L3DOC: Lifelong 3D Object Classification
• Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server
• Self-Supervised GANs via Auxiliary Rotation Loss
• XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
• Solutions to problems with deep learning
• Storing Encoded Episodes as Concepts for Continual Learning
• A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
• Towards Incremental Learning in Large Language Models: A Critical Review
• A Self-Commissioning Edge Computing Method for Data-Driven Anomaly Detection in Power Electronic Systems
• Compositional Visual Generation and Inference with Energy Based Models
• Parameter-Efficient Continual Fine-Tuning: A Survey
• MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning
• Evaluating Online Continual Learning with CALM
• Accelerating Deep Learning Inference via Learned Caches
• Continual Learning through Human-Robot Interaction: Human Perceptions of a Continual Learning Robot in Repeated Interactions
• BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning
• Online Distillation with Continual Learning for Cyclic Domain Shifts
• When Do Curricula Work?
• X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models
• Sound and Complete Neural Network Repair with Minimality and Locality Guarantees
• On Sequential Bayesian Inference for Continual Learning
• Inference of the optical depth to reionization $\tau$ from $\text{Planck}$ CMB maps with convolutional neural networks
• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
• Powerpropagation: A sparsity inducing weight reparameterisation
• Prototype-based Incremental Few-Shot Semantic Segmentation
• Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer
• Continuous Coordination As a Realistic Scenario for Lifelong Learning
• Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
• An Analysis Of Entire Space Multi-Task Models For Post-Click Conversion Prediction
• On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models
• Lifelong Robotic Reinforcement Learning by Retaining Experiences
• Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems
• Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data
• Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings
• Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data
• On the Importance of Difficulty Calibration in Membership Inference Attacks
• Continual Domain Adaptation for Machine Reading Comprehension
• Neural Network Retraining for Model Serving
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting
• On the importance of cross-task features for class-incremental learning
• Energy-Based Models for Continual Learning
• Continual Learning for On-Device Speech Recognition using Disentangled Conformers
• Lifelong Bayesian Optimization
• Continual Referring Expression Comprehension via Dual Modular Memorization
• Differentially Private Continual Learning
• Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification
• Contrastive Supervised Distillation for Continual Representation Learning
• Towards Generalized and Incremental Few-Shot Object Detection
• A Study of Continual Learning Methods for Q-Learning
• F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning
• RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
• NBA: defensive distillation for backdoor removal via neural behavior alignment
• Understanding Continual Learning Settings with Data Distribution Drift Analysis
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain
• Continual Representation Learning for Biometric Identification
• Conditional Computation for Continual Learning
• CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection
• Lifelong Learning of Hate Speech Classification on Social Media
• Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
• ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems
• Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning
• Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
• Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
• Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization
• Benchmarking Spiking Neural Network Learning Methods with Varying Locality
• Continual Domain Randomization
• Continual Model-Based Reinforcement Learning with Hypernetworks
• Multimodal Conditional 3D Face Geometry Generation
• Context-Aware Multipath Networks
• GAN Cocktail: mixing GANs without dataset access
• Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
• On the Costs and Benefits of Adopting Lifelong Learning for Software Analytics -- Empirical Study on Brown Build and Risk Prediction
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning
• An Ultra-Low Power Wearable BMI System with Continual Learning Capabilities
• CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
• Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
• CUCL: Codebook for Unsupervised Continual Learning
• Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domain
• FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
• Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference
• Formalizing the Generalization-Forgetting Trade-off in Continual Learning
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
• DRILL: Dynamic Representations for Imbalanced Lifelong Learning
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments
• Targeted Gradient Descent: A Novel Method for Convolutional Neural Networks Fine-tuning and Online-learning
• Positive-Congruent Training: Towards Regression-Free Model Updates
• Update Frequently, Update Fast: Retraining Semantic Parsing Systems in a Fraction of Time
• Edge Bias in Federated Learning and its Solution by Buffered Knowledge Distillation
• Pseudo-Rehearsal for Continual Learning with Normalizing Flows
• Multi-Domain Multi-Task Rehearsal for Lifelong Learning
• Unifying Regularisation Methods for Continual Learning
• OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning
• Continual Learning Using Bayesian Neural Networks
• Continual Learning via Online Leverage Score Sampling
• Self-Supervised Deep Visual Odometry with Online Adaptation
• HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections
• Towards Continuous Domain adaptation for Healthcare
• Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
• NEUZZ: Efficient Fuzzing with Neural Program Smoothing
• Making Good on LSTMs' Unfulfilled Promise
• How neural networks find generalizable solutions: Self-tuned annealing in deep learning
• Distributed Weight Consolidation: A Brain Segmentation Case Study
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Localizing Catastrophic Forgetting in Neural Networks
• Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning
• Continual Learning Using World Models for Pseudo-Rehearsal
• Continual Learning Using Multi-view Task Conditional Neural Networks
• PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization
• Identifying and Mitigating Machine Learning Biases for the Gravitational Wave Detection Problem
• Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM
• Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector
• Overcoming Catastrophic Forgetting by Neuron-level Plasticity Control
• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
• MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields
• Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning
• VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning
• Learning Language Specific Sub-network for Multilingual Machine Translation
• Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments
• Automatic Construction of Multi-layer Perceptron Network from Streaming Examples
• Personalised Federated Learning: A Combinational Approach
• Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research
• SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation
• Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data
• Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
• Streaming Adaptive Nonparametric Variational Autoencoder
• Continual Learning with Self-Organizing Maps
• Learning to Recommend via Meta Parameter Partition
• Few-Shot Unsupervised Continual Learning through Meta-Examples
• Bayesian Structure Adaptation for Continual Learning
• Training Neural Networks with Fixed Sparse Masks
• Enhancing the accuracies by performing pooling decisions adjacent to the output layer
• TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
• Wide Neural Networks Forget Less Catastrophically
• Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning
• Improving Human Motion Prediction Through Continual Learning
• Continual Learning in Predictive Autoscaling
• Posterior Meta-Replay for Continual Learning
• Meta Continual Learning via Dynamic Programming
• Learning Invariant Representation for Continual Learning
• Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learning
• AE-Net: Autonomous Evolution Image Fusion Method Inspired by Human Cognitive Mechanism
• Bookworm continual learning: beyond zero-shot learning and continual learning
• Thalamocortical contribution to solving credit assignment in neural systems
• Lifelong Learning with Sketched Structural Regularization
• Visually Grounded Continual Learning of Compositional Phrases
• Overcoming Catastrophic Forgetting by Generative Regularization
• Confidence-Guided Learning Process for Continuous Classification of Time Series
• Continual Learning with Fully Probabilistic Models
• Sequoia: A Software Framework to Unify Continual Learning Research
• An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation
• Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition
• Looking for a better fit? An Incremental Learning Multimodal Object Referencing Framework adapting to Individual Drivers
• PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models
• A Combinatorial Perspective on Transfer Learning
• Efficient Architecture Search for Continual Learning
• Detecting Information Relays in Deep Neural Networks
• Model Primitive Hierarchical Lifelong Reinforcement Learning
• Continual Learning from the Perspective of Compression
• Continual Learning in the Presence of Repetition
• Continuous Learning in a Single-Incremental-Task Scenario with Spike Features
• Feature Staleness Aware Incremental Learning for CTR Prediction
• I2CANSAY:Inter-Class Analogical Augmentation and Intra-Class Significance Analysis for Non-Exemplar Online Task-Free Continual Learning
• Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
• Disturbance-immune Weight Sharing for Neural Architecture Search
• 5G-DIL: Domain Incremental Learning with Similarity-Aware Sampling for Dynamic 5G Indoor Localization
• Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learning
• A survey of deep neural network watermarking techniques
• Review, Analysis and Design of a Comprehensive Deep Reinforcement Learning Framework
• Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
• Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay
• Continual Learning with Extended Kronecker-factored Approximate Curvature
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Optimizing Reusable Knowledge for Continual Learning via Metalearning
• Overcoming Catastrophic Interference in Online Reinforcement Learning with Dynamic Self-Organizing Maps
• Time series analysis with dynamic law exploration
• Less-forgetful Learning for Domain Expansion in Deep Neural Networks
• PKI: Prior Knowledge-Infused Neural Network for Few-Shot Class-Incremental Learning
• Reviewing continual learning from the perspective of human-level intelligence
• Lifelong Intent Detection via Multi-Strategy Rebalancing
• Generative Memory for Lifelong Reinforcement Learning
• Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity
• Review learning: Real world validation of privacy preserving continual learning across medical institutions
• A Case for Backward Compatibility for Human-AI Teams
• A contrastive rule for meta-learning
• Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding
• Frosting Weights for Better Continual Training
• Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization
• Memory-Free Generative Replay For Class-Incremental Learning
• FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization
• Fisher Task Distance and Its Application in Neural Architecture Search
• CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
• Towards Open World Object Detection
• Derivative-Free & Order-Robust Optimisation
• Label Mapping Neural Networks with Response Consolidation for Class Incremental Learning
• Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
• MultiConfederated Learning: Inclusive Non-IID Data handling with Decentralized Federated Learning
• GROWN: GRow Only When Necessary for Continual Learning
• Efficient Meta Lifelong-Learning with Limited Memory
• Monitoring multimode processes: a modified PCA algorithm with continual learning ability
• Feedforward Neural Networks for Caching: Enough or Too Much?
• A Neurochaos Learning Architecture for Genome Classification
• Rethinking Experience Replay: a Bag of Tricks for Continual Learning
• Bilevel Continual Learning
• ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation
• Continual Unsupervised Domain Adaptation for Semantic Segmentation
• Consolidated Adaptive T-soft Update for Deep Reinforcement Learning
• Tuning Convolutional Spiking Neural Network with Biologically-plausible Reward Propagation
• Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation
• Efficient Online Bayesian Inference for Neural Bandits
• Overcoming Catastrophic Forgetting by Soft Parameter Pruning
• Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients
• Sequential Targeting: an incremental learning approach for data imbalance in text classification
• Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
• Memory Efficient Class-Incremental Learning for Image Classification
• Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
• Thinkback: Task-SpecificOut-of-Distribution Detection
• Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning
• Adaptive Procedural Task Generation for Hard-Exploration Problems
• Learn-Prune-Share for Lifelong Learning
• MicroCam: Leveraging Smartphone Microscope Camera for Context-Aware Contact Surface Sensing
• Superposed Episodic and Semantic Memory via Sparse Distributed Representation
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• OER: Offline Experience Replay for Continual Offline Reinforcement Learning
• AdaHAT: Adaptive Hard Attention to the Task in Task-Incremental Learning
• Single-Net Continual Learning with Progressive Segmented Training (PST)
• GAN Memory with No Forgetting
• Sage: Using Unsupervised Learning for Scalable Performance Debugging in Microservices
• Improving unsupervised neural aspect extraction for online discussions using out-of-domain classification
• Stochastic thermodynamics of Fisher information
• Multi-task Learning with Gradient Guided Policy Specialization
• Co-Transport for Class-Incremental Learning
• Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension
• Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
• S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification
• Transferable Dialogue Systems and User Simulators
• Incremental Concept Learning via Online Generative Memory Recall
• Invariant Feature Learning for Sensor-based Human Activity Recognition
• Hidden Markov Neural Networks
• Lifelong Learning with Searchable Extension Units
• Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
• Continual Learning at the Edge: An Agnostic IIoT Architecture
• Neural Machine Translation: A Review and Survey
• Continual Learning: Forget-free Winning Subnetworks for Video Representations
• Large Scale Incremental Learning
• RECALL: Rehearsal-free Continual Learning for Object Classification
• I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting
• Variational Auto-Regressive Gaussian Processes for Continual Learning
• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction
• Improved Regret Bound and Experience Replay in Regularized Policy Iteration
• One-Shot Domain Incremental Learning
• LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
• MTIL: Encoding Full History with Mamba for Temporal Imitation Learning
• Disentangle-based Continual Graph Representation Learning
• Incremental Meta-Learning via Indirect Discriminant Alignment
• Continual Learning in Task-Oriented Dialogue Systems
• IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report
• Incremental Embedding Learning via Zero-Shot Translation
• Computational models of learning and synaptic plasticity
• Lifelong Learning for Neural powered Mixed Integer Programming
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• Towards a practical measure of interference for reinforcement learning
• AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training
• FedCCL: Federated Clustered Continual Learning Framework for Privacy-focused Energy Forecasting
• Reducing catastrophic forgetting when evolving neural networks
• Adaptive Compression-based Lifelong Learning
• Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning
• Representation Consolidation for Training Expert Students
• Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering
• Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning
• Accretionary Learning with Deep Neural Networks
• Prototypical quadruplet for few-shot class incremental learning
• Analyzing Multi-Task Learning for Abstractive Text Summarization
• Online Limited Memory Neural-Linear Bandits with Likelihood Matching
• Algorithmic insights on continual learning from fruit flies
• Model-agnostic out-of-distribution detection using combined statistical tests
• A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging
• Learning to Remember from a Multi-Task Teacher
• Stochastic Gradient Descent and Anomaly of Variance-flatness Relation in Artificial Neural Networks
• StackNet: Stacking Parameters for Continual learning
• Power Law in Sparsified Deep Neural Networks
• A dynamic connectome supports the emergence of stable computational function of neural circuits through reward-based learning
• Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling
• A General Class of Transfer Learning Regression without Implementation Cost
• Graph-Based Continual Learning
• Model Aggregation via Good-Enough Model Spaces
• Towards a Universal Continuous Knowledge Base
• A Free-Energy Principle for Representation Learning
• Selective Forgetting of Deep Networks at a Finer Level than Samples
• Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition
• Deep Anomaly Detection by Residual Adaptation
• Stabilizing Elastic Weight Consolidation method in practical ML tasks and using weight importances for neural network pruning
• PolyViT: Co-training Vision Transformers on Images, Videos and Audio
• KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning
• ErrorEraser: Unlearning Data Bias for Improved Continual Learning
• Video Relationship Detection Using Mixture of Experts
• Coordinated Control of Deformation and Flight for Morphing Aircraft via Meta-Learning and Coupled State-Dependent Riccati Equations
• Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity
• MS-Net: A Multi-Path Sparse Model for Motion Prediction in Multi-Scenes
• A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation
• A Conceptual Framework for Lifelong Learning
• Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
• Learn Faster and Forget Slower via Fast and Stable Task Adaptation
• Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
• Predictive Coding Networks and Inference Learning: Tutorial and Survey
• Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation
• DIRA: Dynamic Domain Incremental Regularised Adaptation
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
• Regularization-based Continual Learning for Fault Prediction in Lithium-Ion Batteries
• L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation
• Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learning
• Continual Backprop: Stochastic Gradient Descent with Persistent Randomness
• Revisiting Catastrophic Forgetting in Class Incremental Learning
• An EM Framework for Online Incremental Learning of Semantic Segmentation
• A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
• Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense
• TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion
• DIODE: Dilatable Incremental Object Detection
• WildGait: Learning Gait Representations from Raw Surveillance Streams
• Tuned Compositional Feature Replays for Efficient Stream Learning
• Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift
• Continual Speaker Adaptation for Text-to-Speech Synthesis
• Key-Value Pair-Free Continual Learner via Task-Specific Prompt-Prototype
• How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation
• Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning
• Data Summarization via Bilevel Optimization
• ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP
• No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases
• Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems
• Dynamic Nested Hierarchies: Pioneering Self-Evolution in Machine Learning Architectures for Lifelong Intelligence
• Domain Adaptation for Time series Transformers using One-step fine-tuning
• Bilevel Continual Learning
• Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective
• What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
• Incremental Learning via Rate Reduction
• PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning
• SynSpill: Improved Industrial Spill Detection With Synthetic Data
• Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
• A sparse code increases the speed and efficiency of neuro-dynamic programming for optimal control tasks with correlated inputs
• Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
• Explaining How Deep Neural Networks Forget by Deep Visualization
• Monitoring nonstationary processes based on recursive cointegration analysis and elastic weight consolidation
• Image Captions are Natural Prompts for Text-to-Image Models
• IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
• Continual Learning With Quasi-Newton Methods
• Meta-Learning Strategies through Value Maximization in Neural Networks
• Visually Grounded Continual Language Learning with Selective Specialization
• Demystifying the Effects of Non-Independence in Federated Learning
• Fisher information flow in artificial neural networks
• Combining Audio and Non-Audio Inputs in Evolved Neural Networks for Ovenbird
• Biologically Inspired Visual System Architecture for Object Recognition in Autonomous Systems
• Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
• Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning
• Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
• Selective Replay Enhances Learning in Online Continual Analogical Reasoning
• Learning in Deep Neural Networks Using a Biologically Inspired Optimizer
• Class-Incremental Experience Replay for Continual Learning under Concept Drift
• Estimation of Energy-dissipation Lower-bounds for Neuromorphic Learning-in-memory
• Group and Exclusive Sparse Regularization-based Continual Learning of CNNs
• Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness
• REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
• SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning
• Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
• Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
• Crowdsourcing with Enhanced Data Quality Assurance: An Efficient Approach to Mitigate Resource Scarcity Challenges in Training Large Language Models for Healthcare
• Lifelong Whole Slide Image Analysis: Online Vision-Language Adaptation and Past-to-Present Gradient Distillation
• Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling
• Improvements of Dark Experience Replay and Reservoir Sampling towards Better Balance between Consolidation and Plasticity
• GeMuCo: Generalized Multisensory Correlational Model for Body Schema Learning
• Abstraction Learning
• EXACFS -- A CIL Method to mitigate Catastrophic Forgetting
• Deep Stacked Stochastic Configuration Networks for Lifelong Learning of Non-Stationary Data Streams
• A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC
• Reducing Catastrophic Forgetting in Modular Neural Networks by Dynamic Information Balancing
• Interleaved Multitask Learning with Energy Modulated Learning Progress
• Unsupervised Replay Strategies for Continual Learning with Limited Data
• Efficient and Robust Continual Graph Learning for Graph Classification in Biology
• Self-Net: Lifelong Learning via Continual Self-Modeling
• Programming with Neural Surrogates of Programs
• Beneficial perturbation network for continual learning
• One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
• Learning by Active Forgetting for Neural Networks
• Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting
• Continual Learning for Food Category Classification Dataset: Enhancing Model Adaptability and Performance
• Mixture-of-Variational-Experts for Continual Learning
• Condensed Composite Memory Continual Learning
• Context selectivity with dynamic availability enables lifelong continual learning
• Efficient Continual Learning in Keyword Spotting using Binary Neural Networks
• Class-incremental Learning with Rectified Feature-Graph Preservation
• Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence
• Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning
• Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
• Visualizing and Understanding Vision System
• Knowledge-Adaptation Priors
• Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing
• Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning
• Statistical Mechanical Analysis of Catastrophic Forgetting in Continual Learning with Teacher and Student Networks
• Computational principles of intelligence: learning and reasoning with neural networks
• Reviewing Model Collapse and Countermeasures
• From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python
• OvA-INN: Continual Learning with Invertible Neural Networks
• A General Framework for Analyzing Stochastic Dynamics in Learning Algorithms
• One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning
• RSAC: Regularized Subspace Approximation Classifier for Lightweight Continuous Learning
• Benchmarking Catastrophic Forgetting Mitigation Methods in Federated Time Series Forecasting
• A Biologically Plausible Audio-Visual Integration Model for Continual Learning
• Better Knowledge Retention through Metric Learning
• Shared and Private VAEs with Generative Replay for Continual Learning
• Lethean Attack: An Online Data Poisoning Technique
• Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning
• Towards an Interface Description Template for AI-enabled Systems
• Measuring Information Transfer in Neural Networks
• Lifelong Learning Without a Task Oracle
• Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization
• Association: Remind Your GAN not to Forget
• Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments
• Overcoming Conflicting Data when Updating a Neural Semantic Parser
• Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay -- 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object Classification
• Collaborative Method for Incremental Learning on Classification and Generation
• Kalman Filter Modifier for Neural Networks in Non-stationary Environments
• Applying Incremental Deep Neural Networks-based Posture Recognition Model for Injury Risk Assessment in Construction
• An Algorithm for Learning Smaller Representations of Models With Scarce Data
• Learn to Talk via Proactive Knowledge Transfer
• Lifelong Person Search
• iLGaCo: Incremental Learning of Gait Covariate Factors
• A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors
• Caption, Create, Continue: Continual Learning with Pre-trained Generative Vision-Language Models
• Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint
• Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning
• DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
• Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
• Toward industrial use of continual learning : new metrics proposal for class incremental learning
• Compression-aware Continual Learning using Singular Value Decomposition
• Using Fictitious Class Representations to Boost Discriminative Zero-Shot Learners
• A Meta-Learned Neuron model for Continual Learning
• Class Incremental Online Streaming Learning
• Dendritic Self-Organizing Maps for Continual Learning
• Semi-Supervised Text Classification via Self-Pretraining
• Continual Competitive Memory: A Neural System for Online Task-Free Lifelong Learning
• Rumour Detection via Zero-shot Cross-lingual Transfer Learning
• A Dataset and Baselines for Multilingual Reply Suggestion
• Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning
• Online Continual Learning in Image Classification: An Empirical Survey
• Brain-inspired feature exaggeration in generative replay for continual learning
• Inverse-Hessian Regularization for Continual Learning in ASR
• Does the Adam Optimizer Exacerbate Catastrophic Forgetting?
• Addressee and Response Selection for Multilingual Conversation
• Adapting TTS models For New Speakers using Transfer Learning
• Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environments
• Expressive power of outer product manifolds on feed-forward neural networks
• A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift
• Generating Accurate Virtual Examples For Lifelong Machine Learning
• GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal
• Towards Continual Entity Learning in Language Models for Conversational Agents
• Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers
• Synthesized Trust Learning from Limited Human Feedback for Human-Load-Reduced Multi-Robot Deployments
• Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation
• Interpretable UAV Collision Avoidance using Deep Reinforcement Learning
• Continual Learning of Multi-modal Dynamics with External Memory
• A New Framework for Machine Intelligence: Concepts and Prototype
• Sparse distributed representation, hierarchy, critical periods, metaplasticity: the keys to lifelong fixed-time learning and best-match retrieval
• Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery
• Case-based Reasoning for Natural Language Queries over Knowledge Bases
• DARTS-PRIME: Regularization and Scheduling Improve Constrained Optimization in Differentiable NAS
• Residual Continual Learning
• Geodesic-SVDD Latent Mixup for One-Shot Distributed Tabular Learning
• A good body is all you need: avoiding catastrophic interference via agent architecture search
• Incremental Class Learning using Variational Autoencoders with Similarity Learning
• Efficient Bayesian Updates for Deep Active Learning via Laplace Approximations
• Self-Improving Semantic Perception for Indoor Localisation
• Exploring the Challenges towards Lifelong Fact Learning
• Solving hybrid machine learning tasks by traversing weight space geodesics
• Realizing Continual Learning through Modeling a Learning System as a Fiber Bundle
• FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning
• Training Multi-Layer Binary Neural Networks With Local Binary Error Signals
• Combating catastrophic forgetting with developmental compression
• TAG: Task-based Accumulated Gradients for Lifelong learning
• Meta-Learning a Dynamical Language Model
• Discriminative Distillation to Reduce Class Confusion in Continual Learning
• Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning
• Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
• TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets
• SAFE: Spectral Evolution Analysis Feature Extraction for Non-Stationary Time Series Prediction
• Learning Multiple Categories on Deep Convolution Networks
• Continual Novelty Detection
• High Throughput Training of Deep Surrogates from Large Ensemble Runs
• Lifetime policy reuse and the importance of task capacity
• A Deep Optimization Approach for Image Deconvolution
• A study on the plasticity of neural networks
• Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecasts
• Sometimes You Want to Go Where Everybody Knows your Name
• Lifelong Mixture of Variational Autoencoders
• Lifelong Twin Generative Adversarial Networks
• Embodiment dictates learnability in neural controllers
• IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay
• Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
• Continual learning under domain transfer with sparse synaptic bursting
• MyMigrationBot: A Cloud-based Facebook Social Chatbot for Migrant Populations
• Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
• Dynamic VAEs with Generative Replay for Continual Zero-shot Learning
• CALM: Continuous Adaptive Learning for Language Modeling
• Continuous learning of face attribute synthesis
• Kronecker Factorization for Preventing Catastrophic Forgetting in Large-scale Medical Entity Linking
• Divide and Conquer: Static-Dynamic Collaboration for Few-Shot Class-Incremental Learning
• DPRK-BERT: The Supreme Language Model
• Incrementally Zero-Shot Detection by an Extreme Value Analyzer
• Weighted Ensemble Models Are Strong Continual Learners
• PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks
• Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media
• Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network
• The many faces of deep learning
• Multiple Additive Neural Networks for Structured and Unstructured Data
• ZS-IL: Looking Back on Learned Experiences For Zero-Shot Incremental Learning
• BooVAE: Boosting Approach for Continual Learning of VAE
• Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
• Learning to Continually Learn Rapidly from Few and Noisy Data
• Lifelong Learning based Disease Diagnosis on Clinical Notes
• POET: Prompt Offset Tuning for Continual Human Action Adaptation
• Provable Lifelong Learning of Representations