For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Cascade System of Dynamic Binary Neural Networks and Learning of Periodic Orbit
Jungo MORIYASU Toshimichi SAITO
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/09/01
Online ISSN: 1745-1361
Type of Manuscript: Special Section PAPER (Special Section on Optimization and Learning Algorithms of Small Embedded Devices and Related Software/Hardware Implementation)
binary neural networks, deep learning, switching circuits,
Full Text: PDF>>
This paper studies a cascade system of dynamic binary neural networks. The system is characterized by signum activation function, ternary connection parameters, and integer threshold parameters. As a fundamental learning problem, we consider storage and stabilization of one desired binary periodic orbit that corresponds to control signals of switching circuits. For the storage, we present a simple method based on the correlation learning. For the stabilization, we present a sparsification method based on the mutation operation in the genetic algorithm. Using the Gray-code-based return map, the storage and stability can be investigated. Performing numerical experiments, effectiveness of the learning method is confirmed.