Proceedings of the International Workshop on Applications of Neural Networks to Telecommunications

Programmable VLSI Neural Network Processors for Equalization of Digital Communication Channels

Sa H. Bang, Bing J. Sheu, and Joongho Choi

Department of Electrical EngineeringPowell Hall, Room 604and Signal and Image Processing InstituteUniversity of Southern California, Los Angeles, CA [e-mail]

Abstract

Analog VLSI neural networks are developed for equalization of intersymbol interference and maximum-likelihood sequence estimation. Based on a 4-layered perceptron, the equatizer approximates the optimum receiver. The fabricated chip contains an analog tapped-delay line, (8-12-12-1)-perceptron, and interface circuitry for training. Both simulated and experimental results are presented. A cascadable MLSE receiver using the ...