Summary
International Symposium on Nonlinear Theory and Its Applications
2015
Session Number:B2L-F
Session:
Number:B2L-F-1
Simplified Architecture for Cellular Neural Network Suitable for High-Density Integration of Electron Devices
Mutsumi Kimura, Ryohei Morita, Yuki Koga, Hiroki Nakanishi, Nao Nakamura, Tokiyoshi Matsuda,
pp.499-502
Publication Date:2015/12/1
Online ISSN:2188-5079
DOI:10.34385/proc.47.B2L-F-1
PDF download (248.9KB)
Summary:
We will propose a simplified architecture for a cellular neural network suitable for high-density integration of electron devices. A neuron consists of only eight transistors, and a synapse consists of just only one variable resistor. First, we developed a specialized simulator to estimate the practical operation. Moreover, we emulated the neural network using a field-programmable gate array and trimming resistors. The neural network succeeded in learning multiple logics even in a small-scale network. We think that this result indicates that our proposal has a big potential for future electronics using neural networks.