Title :
A finite physical quantity neural network VLSI with a learning capability
Author :
Watanabe, Minoru ; Kobayashi, Fuminori
Author_Institution :
Dept. of Control Eng. & Sci., Kyushu Inst. of Technol., Fukuoka, Japan
Abstract :
A finite physical quantity neural network (FPQNN) VLSI with a learning capability is proposed. The FPQNN model has a feature that the total electric charge stored in all neurons in a network is monotone decreasing while recalling. Despite the restriction of never increasing, the FPQNN model can produce a good performance for pattern classification. This paper presents an analog circuit implementation with a learning capability that can calculate the movement of electric charge of the FPQNN model precisely and rapidly.
Keywords :
VLSI; analogue circuits; electric charge; leakage currents; learning (artificial intelligence); neural nets; pattern classification; analog circuits; electric charge movement; finite physical quantity neural network VLSI; finite physical quantity neural network model; leakage currents; learning capability; pattern classification;
Conference_Titel :
SICE 2003 Annual Conference
Conference_Location :
Fukui, Japan
Print_ISBN :
0-7803-8352-4
