2010/04/29 by Michael Barber, Michael J. Barber, J. W. Clark +3
Computer Science · Mathematics · Physics and Astronomy · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Artificial intelligence #Artificial neural network #Bayesian Modeling and Causal Inference #Bayesian network #Bayesian probability #Class (philosophy) #Computer science #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine learning #Mathematics #Probabilistic logic #Probabilistic neural network #Process (computing) #Random variable #Statistics #Time Series Analysis and Forecasting #Time delay neural network #cond-mat.dis-nn #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.1004.5326
published in arXiv (Cornell University) (Cornell University) · 13 pages, elsarticle
arxiv created 2010/04/29 · openalex publication_date 2010/04/29 · arxiv updated 2010/04/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
We introduce a class of neural networks derived from probabilistic models in the form of Bayesian networks. By imposing additional assumptions about the nature of the probabilistic models represented in the networks, we derive neural networks with standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the random variables, that can pool multiple sources of evidence, and that deal cleanly and consistently with inconsistent or contradictory evidence. The presented neural networks capture many properties of Bayesian networks, providing distributed versions of probabilistic models.