Summary

2011 International Symposium on Nonlinear Theory and Its Applications

2011

Session Number:B2L-D

Session:

Number:B2L-D4

Multi-Layer Perceptron with Pulse Glial Chain

Chihiro Ikuta,  Yoko Uwate,  Yoshifumi Nishio,  

pp.435-438

Publication Date:2011/9/4

Online ISSN:2188-5079

DOI:10.34385/proc.45.B2L-D4

PDF download (1.4MB)

Summary:
A glia is a nervous cell in the brain. Currently, the glia is known as a important cell for the human’s cerebration. Because the glia transmits signals to neurons and other glias. We notice features of the glia and consider to apply it for an artificial neural network. In this paper, we propose a Multi-layer perceptron (MLP) with pulse glial chain. The pulse glial chain is inspired from the features of the glia. The glia generates a pulse by a connecting neuron and it excites neighborhood neurons and glias. The pulse is generated as different glia, thus, these pulses look like propagating into the network. We show the MLP with pulse glial chain has better performance than the conventional MLP by computer simulations.