An analog neural network processor with programmable topology

Author

Boser, Bernhard E. ; Sackinger, Eduard ; Bromley, Jane ; Le Cun, Yann ; Jackel, Lawrence D.

Author_Institution

AT&T Bell Labs., Holmdel, NJ, USA

Volume

26

Issue

12

fYear

1991

fDate

12/1/1991 12:00:00 AM

Firstpage

2017

Lastpage

2025

Abstract

The architecture, implementation, and applications of a special-purpose neural network processor are described. The chip performs over 2000 multiplications and additions simultaneously. Its data path is particularly suitable for the convolutional topologies that are typical in classification networks, but can also be configured for fully connected or feedback topologies. Resources can be multiplexed to permit implementation of networks with several hundreds of thousands of connections on a single chip. Computations are performed with 6 b accuracy for the weights and 3 b for the neuron states. Analog processing is used internally for reduced power dissipation and higher density, but all input/output is digital to simplify system integration. The practicality of the chip is demonstrated with an implementation of a neural network for optical character recognition. This network contains over 130000 connections and was evaluated in 1 ms

Keywords

CMOS integrated circuits; VLSI; application specific integrated circuits; neural nets; optical character recognition; special purpose computers; 1 ms; 6 bit; CMOS; OCR; analog neural network processor; analog processing internally; classification networks; convolutional topologies; digital input/output; higher density; neural network; optical character recognition; programmable topology; reduced power dissipation; special-purpose neural network processor; Character recognition; Network topology; Neural networks; Neurofeedback; Neurons; Optical character recognition software; Optical computing; Optical feedback; Optical fiber networks; Power dissipation;

fLanguage

English

Journal_Title

Solid-State Circuits, IEEE Journal of

Publisher

ieee

ISSN

0018-9200

Type

jour

DOI

10.1109/4.104196

Filename

104196