Title :
Pulse arithmetic in VLSI neural networks
Author_Institution :
Dept. of Electr. Eng., Edinburgh Univ., UK
Abstract :
This review explores the use of biological signaling methods to build silicon networks. Recent designs using a technique called ´pulse stream´, which employs fully analog, dynamic weight storage, are described. The pulse-stream concept is explained, and a comparison is made with conventional analog neural networks. An analog synapse based on the pulse-stream approach is presented. Chip details and simulation results are given.<>
Keywords :
CMOS integrated circuits; VLSI; analogue computer circuits; linear integrated circuits; neural nets; pulse circuits; VLSI neural networks; analog neural networks; analog synapse; biological signaling methods; dynamic weight storage; pulse arithmetic; pulse stream; silicon networks; simulation results; Analog memory; Arithmetic; Associative memory; Biological neural networks; Intelligent networks; Neural networks; Neurons; Operational amplifiers; Silicon; Very large scale integration;
Journal_Title :
Micro, IEEE
