Learning of Simple Dynamic Binary Neural Networks

Ryota KOUZUKI  Toshimichi SAITO  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E96-A   No.8   pp.1775-1782
Publication Date: 2013/08/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E96.A.1775
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
Keyword: 
neural networks,  supervised learning,  correlation learning,  genetic algorithms,  dc-ac inverters,  

Full Text: PDF>>
Buy this Article




Summary: 
This paper studies the simple dynamic binary neural network characterized by the signum activation function, ternary weighting parameters and integer threshold parameters. The network can be regarded as a digital version of the recurrent neural network and can output a variety of binary periodic orbits. The network dynamics can be simplified into a return map, from a set of lattice points, to itself. In order to store a desired periodic orbit, we present two learning algorithms based on the correlation learning and the genetic algorithm. The algorithms are applied to three examples: a periodic orbit corresponding to the switching signal of the dc-ac inverter and artificial periodic orbit. Using the return map, we have investigated the storage of the periodic orbits and stability of the stored periodic orbits.