Journal
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
Volume 51, Issue 1, Pages 103-115Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSMC.2020.3043249
Keywords
Bidirectional associative memory (BAM); bidirectional backpropagation; global stability; Hebbian learning
Ask authors/readers for more resources
Bidirectional associative memories (BAMs) pass neural signals forward and backward through the same network of synapses. These memories can adjust synaptic weights using unsupervised learning and can be extended to arbitrary hidden layers with proper bidirectional backpropagation algorithms.
Bidirectional associative memories (BAMs) pass neural signals forward and backward through the same web of synapses. Earlier BAMs had no hidden neurons and did not use supervised learning. They tuned their synaptic weights with unsupervised Hebbian or competitive learning. Two-layer feedback BAMs always converge to fixed-point equilibria for threshold or threshold-like neurons. Every rectangular connection matrix is bidirectionally stable. These simpler BAMs extend to arbitrary hidden layers with supervised learning if the resulting bidirectional backpropagation algorithm uses the proper layer likelihood in the forward and backward directions. Bidirectional backpropagation lets users run deep classifiers and regressors in reverse as well as forward. Bidirectional training exploits pattern and synaptic information that forward-only running ignores.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available