Applications of random-pulse machine concept to neural network design

Author

Petriu, Emil M. ; Watanabe, Kenzo ; Yeap, Tet H.

Author_Institution

Dept. of Electr. Eng., Ottawa Univ., Ont., Canada

Volume

45

Issue

2

fYear

1996

fDate

4/1/1996 12:00:00 AM

Firstpage

665

Lastpage

669

Abstract

Neural networks can reach their true potential only when they are implemented in hardware as massively parallel processors. This paper presents the random-pulse machine concept and shows how it can be used for the modular design of neural networks. Random-pulse machines deal with analog variables represented by the mean rate of random-pulse streams and use simple digital technology to perform arithmetic and logic operations. This concept presents a good tradeoff between the electronic circuit complexity and the computational accuracy. The resulting neural network architecture has a high packing density and is well suited for very large-scale integration (VLSI). Simulation results illustrate the performance of the basic elements of a random-pulse neuron

Keywords

VLSI; computational complexity; digital arithmetic; neural net architecture; quantisation (signal); random processes; VLSI; analog variables; arithmetic operations; computational accuracy; digital technology; electronic circuit complexity; logic operations; massively parallel processors; mean rate; modular design; neural network design; packing density; random-pulse machine; random-pulse neuron; simulation; very large-scale integration; Circuit simulation; Computational modeling; Computer architecture; Digital arithmetic; Electronic circuits; Large scale integration; Logic; Neural network hardware; Neural networks; Very large scale integration;

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/19.492806

Filename

492806