Affiliation:
1. Department of Computer Science, University of Toronto, 10 King's College Road, Toronto M5S 1A4, Canada
Abstract
The Boltzmann machine learning procedure has been successfully applied in deterministic networks of analog units that use a mean field approximation to efficiently simulate a truly stochastic system (Peterson and Anderson 1987). This type of “deterministic Boltzmann machine” (DBM) learns much faster than the equivalent “stochastic Boltzmann machine” (SBM), but since the learning procedure for DBM's is only based on an analogy with SBM's, there is no existing proof that it performs gradient descent in any function, and it has only been justified by simulations. By using the appropriate interpretation for the way in which a DBM represents the probability of an output vector given an input vector, it is shown that the DBM performs steepest descent in the same function as the original SBM, except at rare discontinuities. A very simple way of forcing the weights to become symmetrical is also described, and this makes the DBM more biologically plausible than back-propagation (Werbos 1974; Parker 1985; Rumelhart et al. 1986).
Subject
Cognitive Neuroscience,Arts and Humanities (miscellaneous)
Cited by
121 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A biologically plausible parser with Kleene star operation;International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023);2023-12-07
2. Hybrid Deep Neural Network for Alpaca Animal Recognition: Achieving High Accuracy in Detection and Classification;2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS);2023-11-01
3. Connectionist Models of Cognition;The Cambridge Handbook of Computational Cognitive Sciences;2023-05-11
4. Cognitive Modeling Paradigms;The Cambridge Handbook of Computational Cognitive Sciences;2023-05-11
5. Application of machine learning, deep learning and optimization algorithms in geoengineering and geoscience: Comprehensive review and future challenge;Gondwana Research;2022-09