Designing neural networks that process mean values of random variables |
| |
Institution: | 1. AIT Austrian Institute of Technology, Innovation Systems Department, 1220 Vienna, Austria;2. Department of Physics and McDonnell Center for the Space Sciences, Washington University, St. Louis, MO 63130, United States;3. Centro de Ciências Matemáticas, Universidade de Madeira, 9000-390 Funchal, Portugal |
| |
Abstract: | We develop a class of neural networks derived from probabilistic models posed in the form of Bayesian networks. Making biologically and technically plausible assumptions about the nature of the probabilistic models to be represented in the networks, we derive neural networks exhibiting standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the relevant random variables, that can pool multiple sources of evidence, and that deal appropriately with ambivalent, inconsistent, or contradictory evidence. |
| |
Keywords: | Neural networks Probabilistic models Bayesian networks Bayesian inference Neural information processing Population coding |
本文献已被 ScienceDirect 等数据库收录! |
|