Dynamic learning of neural network by analog electronic circuits

Authors:
Masashi Kawaguchi;Takashi Jimbo;Naohiro Ishii
Affiliations:
Department of Electrical & Electronic Engineering, Suzuka National College of Technology, Suzuka Mie, Japan;Department of Environmental Technology and Urban Planning Graduate School of Engineering, Nagoya Institute of Technology, Nagoya, Japan;Department of Information Science, Aichi Institute of Technology, Toyota, Japan
Venue:
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part IV
Year:
2011

Citing 2
Cited 0

Analog VLSI and neural systems

Analog VLSI and neural systems
Analog VLSI Layout Design and the Circuit Board Manufacturing of Advanced Image Processing for Artificial Vision Model

KES '08 Proceedings of the 12th international conference on Knowledge-Based Intelligent Information and Engineering Systems, Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the neural network field, many application models have been proposed. A neuro chip and an artificial retina chip are developed to comprise the neural network model and simulate the biomedical vision system. Previous analog neural network models were composed of the operational amplifier and fixed resistance. It is difficult to change the connection coefficient. In this study, we used analog electronic multiple circuits. The connecting weights describe the input voltage. It is easy to change the connection coefficient. This model works only on analog electronic circuits. It can finish the learning process in a very short time and this model will enable more flexible learning.