Discrete Variational Autoencoders
Explore this paper's citation graph
Summary
A novel method to train a class of probabilistic models with discrete latent variables using the variational autoencoder framework, including backpropagation through the discrete hidden variables, which outperforms state-of-the-art methods on the permutation-invariant MNIST, Omniglot, and Caltech-101 Silhouettes datasets.
- Type
- preprint
- Published
- 2016-09-07
- Cited by
- 291
- References
- 62
- Access
- Open access
- OpenAlex
- https://openalex.org/W2519430864
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11663659
Keywords
Probabilistic logic, MNIST database, Artificial intelligence, Autoencoder, Component (thermodynamics)
References
- Deep Boltzmann Machines
- A Recurrent Latent Variable Model for Sequential Data
- Techniques for Learning Binary Stochastic Feedforward Neural Networks
- An Introduction to Variational Methods for Graphical Models
- Learning Deep Generative Models with Doubly Stochastic MCMC
- Accurate and conservative estimates of MRF log-likelihood using reverse annealing
- Information processing in dynamical systems: foundations of harmony theory
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Auto-Encoding Variational Bayes
- Sequential updating of conditional probabilities on directed graphical structures
- Approximating Probabilistic Inference in Bayesian Belief Networks is NP-Hard
- Replica Monte Carlo simulation of spin glasses.
- Statistically optimal analysis of samples from multiple equilibrium states.
- Connectionist Learning of Belief Networks
- Dropout: a simple way to prevent neural networks from overfitting
- On the quantitative analysis of deep belief networks
- Deep AutoRegressive Networks
- Autoencoders, Minimum Description Length and Helmholtz Free Energy
- Semi-supervised Learning with Deep Generative Models
- Gradient-based learning applied to document recognition
Cited by
- Variational Lossy Autoencoder
- PixelVAE: A Latent Variable Model for Natural Images
- Semi-Supervised Generation with Cluster-aware Generative Models
- Stochastic Sequential Neural Networks with Structured Inference
- Piecewise Latent Variables for Neural Variational Text Processing
- Energy-based Models for Video Anomaly Detection
- Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
- Advances in Variational Inference
- Semi-Amortized Variational Autoencoders
- DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
- Associative Compression Networks for Representation Learning
- Revisiting Reweighted Wake-Sleep
- Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding
- Deep Generative Models for Semi-Supervised Machine Learning
- Structured Inference for Recurrent Hidden Semi-markov Model
- Task-oriented learning of structured probability distributions
- Generative models for natural images
- Expanding variational autoencoders for learning and exploiting latent representations in search distributions
- Hierarchical Quantized Representations for Script Generation
- Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks