Connectionist learning of belief networks

1992/07/01 by Radford M. Neal · 540 citations
Computer Science · #Artificial intelligence #Artificial neural network #Bayesian Modeling and Causal Inference #Boltzmann machine #Computer science #Connectionism #Domain Adaptation and Few-Shot Learning #Machine learning #Neural Networks and Applications #Probabilistic logic #Representation (politics) #Restricted Boltzmann machine #Sigmoid function #Unsupervised learning

paper · doi:10.1016/0004-3702(92)90065-6

published in Artificial Intelligence 56(1), 71-113 (Elsevier BV)

openalex publication_date 1992/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/23

Cited by

• Decoding-based Regression
• Tails of Lipschitz Triangular Flows
• Analogy as Nonparametric Bayesian Inference over Relational Systems
• Neural Propagation of Beliefs
• Reweighted Expectation Maximization
• Deep Restricted Boltzmann Networks
• A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition
• Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
• Pixel Recurrent Neural Networks
• Representation Learning: A Review and New Perspectives
• Overdispersed Black-Box Variational Inference
• A Survey on Bayesian Deep Learning
• Breaking the Curse with BAND: Nonparametric Distribution Estimation in High Dimensions
• Training Products of Experts by Minimizing Contrastive Divergence
• Representing and Combining Partially Specified CPTs
• Representation Learning: A Review and New Perspectives
• Simplified Stochastic Feedforward Neural Networks
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• GO Gradient for Expectation-Based Objectives
• Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
• Latent Regression Bayesian Network for Data Representation
• Estimating Well-Performing Bayesian Networks using Bernoulli Mixtures
• Techniques for Learning Binary Stochastic Feedforward Neural Networks
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Universality and kernel-adaptive training for classically trained, quantum-deployed generative models
• Generative Image Modeling Using Spatial LSTMs
• Deep Temporal Sigmoid Belief Networks for Sequence Modeling
• Neural Representation of Probabilistic Information
• A Fast Learning Algorithm for Deep Belief Nets
• Semi-Implicit Generative Model
• Variational inference for Monte Carlo objectives
• Entanglement and optimization within autoregressive neural quantum states
• Neural Autoregressive Distribution Estimation
• Kalman Bayesian Transformer
• Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models
• Unsupervised Learning with Truncated Gaussian Graphical Models
• Implicit Maximum Likelihood Estimation
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• Generative Moment Matching Networks
• Deep Poisson gamma dynamical systems
• Activation Functions: Comparison of trends in Practice and Research for Deep Learning
• VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuits
• Towards Bayesian Deep Learning: A Framework and Some Existing Methods
• Learning Wake-Sleep Recurrent Attention Models
• The Poisson Gamma Belief Network
• Computing Upper and Lower Bounds on Likelihoods in Intractable Networks
• Herding Dynamic Weights for Partially Observed Random Field Models
• Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing
• Structure Learning of Probabilistic Graphical Models: A Comprehensive Survey
• Learning to Generate with Memory
• Nonlinear Statistical Learning with Truncated Gaussian Graphical Models
• Text Segmentation Using Exponential Models
• The Thermodynamic Variational Objective
• Learning Bayesian Networks with Local Structure
• On the Locality of the Natural Gradient for Deep Learning
• Constructing Deep Neural Networks by Bayesian Network Structure Learning
• Speaker Recognition using Deep Belief Networks
• Large Margin Boltzmann Machines and Large Margin Sigmoid Belief Networks
• Factored Temporal Sigmoid Belief Networks for Sequence Learning
• Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization
• Generative learning for deep networks
• IPF for Discrete Chain Factor Graphs
• Designing neural networks that process mean values of random variables
• A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks
• An End-to-End Neural Network for Polyphonic Piano Music Transcription
• Correlated Non-Parametric Latent Feature Models
• Network Fragments: Representing Knowledge for Constructing Probabilistic\n Models
• Learning to represent visual input. [europepmc]
• Nonlinear spike-and-slab sparse coding for interpretable image encoding. [europepmc]
• Learning Probabilistic Inference through Spike-Timing-Dependent Plasticity. [europepmc]
• Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images. [europepmc]
• Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types. [europepmc]
• Probabilistic Circuits for Autonomous Learning: A Simulation Study. [europepmc]
• Hardware implementation of Bayesian network building blocks with stochastic spintronic devices. [europepmc]
• Hardware Design for Autonomous Bayesian Networks. [europepmc]
• Big Data to Knowledge: Application of Machine Learning to Predictive Modeling of Therapeutic Response in Cancer. [europepmc]
• Probabilistic computing using Cu 0.1 Te 0.9 /HfO 2 /Pt diffusive memristors. [europepmc]
• PheSeq, a Bayesian deep learning model to enhance and interpret the gene-disease association studies. [europepmc]
• An overview of critical applications of resistive random access memory. [europepmc]
• Predicting implantation by using dual AI system incorporating three-dimensional blastocyst image and conventional embryo evaluation parameters-A pilot study. [europepmc]
• Automatic Extraction and Compensation of P-Bit Device Variations in Large Array Utilizing Boltzmann Machine Training. [europepmc]