Title :
Analog CMOS current-mode implementation of the feedforward neural network with on-chip learning and storage
Author :
Lan, Jeng-Feng ; Wu, Chung-Yu
Author_Institution :
Dept. of Electron. Eng. & Inst. of Electron., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
Based on the outstar structure and the ratio memory, a feedforward Hamming neural network with on-chip learning and storage is designed in CMOS current-mode circuits. The implemented feedforward net can be used as a pattern classifier. The chip of the feedforward Hamming net has been fabricated by 0.8 μm double-poly double-metal n-well CMOS process. The experimental results show that the ratio memory has the contrast enhancement characteristic. Also, the classifier can recognize the distorted pattern which is darken, brighten, level-shifted, or noisy of the exemplar pattern with gray level recognition capability
Keywords :
CMOS analogue integrated circuits; analogue processing circuits; feedforward neural nets; integrated memory circuits; learning systems; neural chips; pattern classification; analog CMOS current-mode; double-poly double-metal n-well CMOS; feedforward Hamming net; feedforward neural network; neural chip; on-chip learning; on-chip storage; outstar structure; pattern classifier; ratio memory; CMOS memory circuits; CMOS process; Current mode circuits; Feedforward neural networks; Image storage; Master-slave; Network-on-a-chip; Neural networks; Neurons; Noise level; Pattern matching; Pattern recognition; Semiconductor device measurement;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488256
