Learning of dynamic BNN toward storing-and-stabilizing periodic patterns

Authors:
Ryo Ito;Yuta Nakayama;Toshimichi Saito
Affiliations:
Hosei University, Tokyo, Japan;Hosei University, Tokyo, Japan;Hosei University, Tokyo, Japan
Venue:
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
Year:
2011

Citing 4
Cited 0

Universal perceptron and DNA-like learning algorithm for binary neural networks: non-LSBF implementation

IEEE Transactions on Neural Networks
Evaluation of Distance Measures for Speciated Evolutionary Neural Networks in Pattern Classification Problems

ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
A GA-based flexible learning algorithm with error tolerance for digital binary neural networks

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
The geometrical learning of binary neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper studies learning algorithm of a dynamic binary neural network having rich dynamics. The algorithm is based on the genetic algorithm with an effective kernel chromosome and hidden neuron sharing. Performing basic numerical experiments, we have confirmed that the algorithm can store desired periodic teacher signals and the stored signals are stable for initial value.