Connectionist learning of belief networks

DOI10.1016/0004-3702(92)90065-6zbMath0761.68081OpenAlexW2083380015MaRDI QIDQ1193492

Radford M. Neal

Publication date: 27 September 1992

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0004-3702(92)90065-6

zbMATH Keywords

Boltzmann machinesgradient ascent learningprobabilistic belief networksprobabilistic knowledgesigmoid and noisy-OR varieties

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Knowledge representation (68T30)

Related Items (24)

Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest ⋮ Neural Representation of Probabilistic Information ⋮ An Efficient Learning Procedure for Deep Boltzmann Machines ⋮ Multinomial Bayesian Learning for Modeling Classical and Nonclassical Receptive Field Properties ⋮ Generalizations of the noisy-or model ⋮ Using hidden nodes in Bayesian networks ⋮ Fast structured prediction using large margin sigmoid belief networks ⋮ On the locality of the natural gradient for learning in deep Bayesian networks ⋮ Energy-Based Models with Applications to Speech and Language Processing ⋮ Structural learning of mixed noisy-or Bayesian networks ⋮ A backpropagation learning algorithm with graph regularization for feedforward neural networks ⋮ Timescale Separation in Recurrent Neural Networks ⋮ Deep Belief Networks Are Compact Universal Approximators ⋮ A simultaneous perturbation weak derivative estimator for stochastic neural networks ⋮ Bayesian networks with a logistic regression model for the conditional probabilities ⋮ Sequentially allocated merge-split samplers for conjugate Bayesian nonparametric models ⋮ A Tighter Bound for Graphical Models ⋮ Designing neural networks that process mean values of random variables ⋮ The shape Boltzmann machine: a strong model of object shape ⋮ On the relative expressiveness of Bayesian and neural networks ⋮ A Fast Learning Algorithm for Deep Belief Nets ⋮ A comprehensive survey and analysis of generative models in machine learning ⋮ Varieties of Helmholtz machine ⋮ Training Products of Experts by Minimizing Contrastive Divergence

Uses Software

• AutoClass

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Evidential reasoning using stochastic simulation of causal models
• Sequential updating of conditional probabilities on directed graphical structures
• Sampling-Based Approaches to Calculating Marginal Densities
• Probabilistic Inference and Influence Diagrams
• An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition
• Equation of State Calculations by Fast Computing Machines
• Learning representations by back-propagating errors

This page was built for publication: Connectionist learning of belief networks