Implementing Neural Nets with Programmable Logic

Abstract

This paper presents networks of Boolean programmable logic modules as one purely digital class of artificial neural nets. The approach contrasts with the continuous analog framework usually suggested.
Programmable logic networks are capable of handling many neural net applications and avoid some of the limitations of threshold logic networks. The approach offers definite advantages for VLSI implementation, namely, a regular architecture with limited connectivity, simplicity of the control machinery, natural modularity, and the support of a mature technology.

IEEE TRANSACTIONS ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL. 36, NO. 7, JULY 1988