An Introduction to Variational Autoencoders

Abstract

Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.

References in corpus (22)

• Semi-Supervised Learning with Deep Generative Models
• NICE: Non-linear Independent Components Estimation
• Weight Uncertainty in Neural Networks
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Variational Graph Auto-Encoders
• Deep Convolutional Inverse Graphics Network
• Generative Moment Matching Networks
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• MADE: Masked Autoencoder for Distribution Estimation
• Variational Lossy Autoencoder
• Neural Photo Editing with Introspective Adversarial Networks
• Learning Stochastic Recurrent Networks
• Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
• Variational Bayesian Inference with Stochastic Search
• Neural Episodic Control
• Deep Probabilistic Programming
• Improving Variational Auto-Encoders using Householder Flow
• PixelVAE: A Latent Variable Model for Natural Images
• Automated Variational Inference in Probabilistic Programming
• Semantic Facial Expression Editing using Autoencoded Flow
• Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow

Cited by in corpus (206)

• Recent advances and clinical applications of deep learning in medical image analysis
• A Unifying Review of Deep and Shallow Anomaly Detection
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• Social physics
• Deep learning in nano-photonics: inverse design and beyond
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Machine Learning in Aerodynamic Shape Optimization
• Dynamical Variational Autoencoders: A Comprehensive Review
• Generative AI Literacy: Twelve Defining Competencies
• Generative AI in the Construction Industry: Opportunities & Challenges
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• AtomAI: A Deep Learning Framework for Analysis of Image and Spectroscopy Data in (Scanning) Transmission Electron Microscopy and Beyond
• Distributed physics informed neural network for data-efficient solution to partial differential equations
• Review: Deep Learning in Electron Microscopy
• Random Partitioning Forest for Point-Wise and Collective Anomaly Detection -- Application to Intrusion Detection
• Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models
• Adaptive deep learning framework for robust unsupervised underwater image enhancement
• Foundation Models in Radiology: What, How, When, Why and Why Not
• Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation
• Understanding Event-Generation Networks via Uncertainties
• Deep learning enabled design of complex transmission matrices for universal optical components
• Exploring order parameters and dynamic processes in disordered systems via variational autoencoders
• GANplifying Event Samples
• Forecasting Covid-19 dynamics in Brazil: a data driven approach
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Generative Networks for Precision Enthusiasts
• Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoil
• Generative AI and Process Systems Engineering: The Next Frontier
• Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
• Neural-network quantum state tomography
• Machine Learning in NextG Networks via Generative Adversarial Networks
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
• A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction
• Synthesizing Optical and SAR Imagery From Land Cover Maps and Auxiliary Raster Data
• C2Ideas: Supporting Creative Interior Color Design Ideation with Large Language Model
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Hybrid Classical-Quantum Autoencoder for Anomaly Detection
• Presenting Unbinned Differential Cross Section Results
• Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• Artificial intelligence and machine learning applications for cultured meat
• Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques
• Generative Capacity of Probabilistic Protein Sequence Models
• Generating Multivariate Load States Using a Conditional Variational Autoencoder
• Creativity and Machine Learning: A Survey
• Roadmap on machine learning glassy dynamics
• Quantum-Noise-Driven Generative Diffusion Models
• Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
• Symmetry meets AI
• Machine Learning-Driven Process of Alumina Ceramics Laser Machining
• Point Set Voting for Partial Point Cloud Analysis
• Stabilizing Invertible Neural Networks Using Mixture Models
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Fully probabilistic deep models for forward and inverse problems in parametric PDEs
• Exploring particle dynamics during self-organization processes via rotationally invariant latent representations
• Towards a Deep Learning Model for Hadronization
• Variational Autoencoder based Metamodeling for Multi-Objective Topology Optimization of Electrical Machines
• Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables
• Hybrid quantum cycle generative adversarial network for small molecule generation
• Learning to Simulate Daily Activities via Modeling Dynamic Human Needs
• High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks
• Toward a Better Monitoring Statistic for Profile Monitoring via Variational Autoencoders
• Euclid preparation XXVI. The Euclid Morphology Challenge. Towards structural parameters for billions of galaxies
• Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations
• Analog ensemble data assimilation and a method for constructing analogs with variational autoencoders
• Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation
• Semi-supervised source localization with deep generative modeling
• Variational Autoencoder Leveraged MMSE Channel Estimation
• Anomaly Detection under Coordinate Transformations
• Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
• 3D-Var Data Assimilation using a Variational Autoencoder
• Leveraging Variational Autoencoders for Parameterized MMSE Estimation
• Revisiting Bayesian Autoencoders with MCMC
• A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them
• Introducing Latent Timbre Synthesis
• Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-wave Detectors
• Inverse design with flexible design targets via deep learning: Tailoring of electric and magnetic multipole scattering from nano-spheres
• Enhancing Continuous Time Series Modelling with a Latent ODE-LSTM Approach
• A semi-supervised approach to dark matter searches in direct detection data with machine learning
• Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room
• Physics-informed Score-based Diffusion Model for Limited-angle Reconstruction of Cardiac Computed Tomography
• ELSA -- Enhanced latent spaces for improved collider simulations
• Experimental Investigation of Machine Learning based Soft-Failure Management using the Optical Spectrum
• Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier
• From observations to complexity of quantum states via unsupervised learning
• Fundamental problems in statistical physics XIV: Lecture on Machine Learning
• KilonovaNet: Surrogate Models of Kilonova Spectra with Conditional Variational Autoencoders
• Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets
• Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis
• Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
• Realistic galaxy images and improved robustness in machine learning tasks from generative modelling
• Generalized Normalizing Flows via Markov Chains
• A Generative Model of Galactic Dust Emission Using Variational Inference
• Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing
• Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement
• Deep learning based Meta-modeling for Multi-objective Technology Optimization of Electrical Machines
• Fairness through Aleatoric Uncertainty
• Jarzynski-like Equality of Nonequilibrium Information Production Based on Quantum Cross Entropy
• Separability, Contextuality, and the Quantum Frame Problem
• Reduced Order Modeling with Shallow Recurrent Decoder Networks
• Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
• Deep learning for nano-photonic materials -- The solution to everything!?
• This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation
• Deception for Cyber Defence: Challenges and Opportunities
• Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars
• Classification and reconstruction of optical quantum states with deep neural networks
• On generative models of T-cell receptor sequences
• Detecting dense-matter phase transition signatures in neutron star mass-radius measurements as data anomalies using normalising flows
• Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines
• Multi-task Batch Reinforcement Learning with Metric Learning
• Training Process of Unsupervised Learning Architecture for Gravity Spy Dataset
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
• Diffusion-Based Surrogate Modeling and Multi-Fidelity Calibration
• Variational encoder geostatistical analysis (VEGAS) with an application to large scale riverine bathymetry
• SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
• Channel Estimation in Underdetermined Systems Utilizing Variational Autoencoders
• Conditional Noise Deep Learning for Parameter Estimation of Gravitational Wave Events
• Electric Vehicle Charging Station Location Selection using Geospatial Artificial Intelligence (GeoAI)
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Variational Autoencoder for Channel Estimation: Real-World Measurement Insights
• Unraveling the Impact of Initial Choices and In-Loop Interventions on Learning Dynamics in Autonomous Scanning Probe Microscopy
• Generating Contextual Load Profiles Using a Conditional Variational Autoencoder
• Unsupervised learning of ferroic variants from atomically resolved STEM images
• Data Driven Control with Learned Dynamics: Model-Based versus Model-Free Approach
• MeLIME: Meaningful Local Explanation for Machine Learning Models
• Parametrization of sunspot groups based on machine learning approach
• Effectiveness of denoising diffusion probabilistic models for fast and high-fidelity whole-event simulation in high-energy heavy-ion experiments
• Analyzing and Unifying Robustness Measures for Excitation Transfer Control in Spin Networks
• Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning
• Generating Gameplay-Relevant Art Assets with Transfer Learning
• VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
• A Bayesian Gaussian Process-Based Latent Discriminative Generative Decoder (LDGD) Model for High-Dimensional Data
• How to GAN Event Unweighting
• Variational Autoencoder Kernel Interpretation and Selection for Classification
• Single-Channel Speech Enhancement with Deep Complex U-Networks and Probabilistic Latent Space Models
• DiffDefense: Defending against Adversarial Attacks via Diffusion Models
• Hyperbolic Deep Learning for Foundation Models: A Survey
• A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps
• A Method to Decipher "Genome" from Interatomic Cohesion in the Exploration for a "Central Dogma" Replacement in Material Science
• Information compression via hidden subgroup quantum autoencoders
• Quantum Inception Score
• Visual Hindsight Self-Imitation Learning for Interactive Navigation
• Evaluating the Stability of Deep Learning Latent Feature Spaces
• Conditional variational autoencoder inference of neutron star equation of state from astrophysical observations
• Variational Bayesian surrogate modelling with application to robust design optimisation
• GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
• Application of the Variational Autoencoder to Detect the Critical Points of the Anisotropic Ising Model
• CSI Clustering with Variational Autoencoding
• A Survey of Features Used for Representing Black-box Single-objective Continuous Optimization
• Score-based Diffusion Models for Bayesian Image Reconstruction
• Effect of latent space distribution on the segmentation of images with multiple annotations
• The application of encoder-decoder neural networks in high accuracy and efficiency slit-scan emittance measurements
• A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
• An Evaluation Study of Generative Adversarial Networks for Collaborative Filtering
• Physics-informed neural networks via stochastic Hamiltonian dynamics learning
• Improving link prediction accuracy of network embedding algorithms via rich node attribute information
• Energy-Based Models with Applications to Speech and Language Processing
• Feature Space Exploration For Planning Initial Benthic AUV Surveys
• LHC Hadronic Jet Generation Using Convolutional Variational Autoencoders with Normalizing Flows
• Face Reconstruction with Variational Autoencoder and Face Masks
• Principled Interpolation in Normalizing Flows
• An Attribute-Aligned Strategy for Learning Speech Representation
• Datacube segmentation via Deep Spectral Clustering
• Variational Inference for Deep Probabilistic Canonical Correlation Analysis
• Deep learning and differential equations for modeling changes in individual-level latent dynamics between observation periods
• Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences
• AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning
• SV-DRR: High-Fidelity Novel View X-Ray Synthesis Using Diffusion Model
• VAE-based Feature Disentanglement for Data Augmentation and Compression in Generalized GNSS Interference Classification
• Input-Output Optics as a Causal Time Series Mapping: A Generative Machine Learning Solution
• Monte Carlo guided Diffusion for Bayesian linear inverse problems
• A Vertical Federated Learning Method For Multi-Institutional Credit Scoring: MICS
• Anchor Prediction: A Topic Modeling Approach
• Deeply-Learned Generalized Linear Models with Missing Data
• Probabilistic partition of unity networks for high-dimensional regression problems
• Model Order Selection with Variational Autoencoding
• Conditional Autoencoder for Generating Binary Neutron Star Waveforms with Tidal and Precession Effects
• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
• Ladder Bottom-up Convolutional Bidirectional Variational Autoencoder for Image Translation of Dotted Arabic Expiration Dates
• Quantifying imperfect cognition via achieved information gain
• Robot at the Mirror: Learning to Imitate via Associating Self-supervised Models
• On the Impact of Sampling on Deep Sequential State Estimation
• Autoencoder-based analytic continuation method for strongly correlated quantum systems
• PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
• Energy based diffusion generator for efficient sampling of Boltzmann distributions
• Estimating Stochastic Poisson Intensities Using Deep Latent Models
• SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems
• Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder
• ParaStyleTTS: Toward Efficient and Robust Paralinguistic Style Control for Expressive Text-to-Speech Generation
• Hierarchical Variational Autoencoder for Visual Counterfactuals
• Physical discovery in representation learning via conditioning on prior knowledge: applications for ferroelectric domain dynamics
• A Deeper Look at the Unsupervised Learning of Disentangled Representations in $\beta$-VAE from the Perspective of Core Object Recognition
• Probabilistic Autoencoder using Fisher Information
• Multiscale Vector-Quantized Variational Autoencoder for Endoscopic Image Synthesis
• Enhance Convolutional Neural Networks with Noise Incentive Block
• Intrinsic Dimension Estimating Autoencoder (IDEA) Using CancelOut Layer and a Projected Loss
• Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
• The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
• Variational autoencoder for generating realistic $N$-body simulations for dark matter halos
• Gamma-Ray Burst Light Curve Reconstruction: A Comparative Machine and Deep Learning Analysis
• Interpreting Equivariant Representations
• Prior Density Learning in Variational Bayesian Phylogenetic Parameters Inference
• Advances in Neural 3D Mesh Texturing: A Survey
• Taming Audio VAEs via Target-KL Regularization
• Enhancing variational generation through self-decomposition