Learning of Simple Dynamic Binary Neural Networks

Ryota KOUZUKI  Toshimichi SAITO  

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
neural networks,  supervised learning,  correlation learning,  genetic algorithms,  dc-ac inverters,  

Full Text: PDF>>
Buy this Article

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.