Hardware requirements for neural network pattern classifiers: a case study and implementation

Author

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

Volume

12

Issue

1

fYear

1992

Firstpage

32

Lastpage

40

Abstract

A special-purpose chip, optimized for computational needs of neural networks and performing over 2000 multiplications and additions simultaneously, is described. Its data path is particularly suitable for the convolutional architectures typical in pattern classification networks but can also be configured for fully connected or feedback topologies. A development system permits rapid prototyping of new applications and analysis of the impact of the specialized hardware on system performance. The power and flexibility of the processor are demonstrated with a neural network for handwritten character recognition containing over 133000 connections.<>

Keywords

computerised pattern recognition; neural nets; convolutional architectures; data path; development system; handwritten character recognition; neural network; pattern classification networks; pattern classifiers; rapid prototyping; special-purpose chip; Computer architecture; Computer networks; Network topology; Neural network hardware; Neural networks; Neurofeedback; Pattern classification; Performance analysis; Prototypes; System performance;

fLanguage

English

Journal_Title

Micro, IEEE

Publisher

ieee

ISSN

0272-1732

Type

jour

DOI

10.1109/40.124378

Filename

124378