Application of the ANNA neural network chip to high-speed character recognition

E Sackinger; B E Boser; J Bromley; Y Lecun; L D Jackel

doi:10.1109/72.129422

Application of the ANNA neural network chip to high-speed character recognition

IEEE Trans Neural Netw. 1992;3(3):498-505. doi: 10.1109/72.129422.

Authors

E Sackinger¹, B E Boser, J Bromley, Y Lecun, L D Jackel

Affiliation

¹ ATandT Bell Labs., Holmdel, NJ.

PMID: 18276453
DOI: 10.1109/72.129422

Abstract

A neural network with 136000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network chip. The neural network chip is capable of processing 1000 characters/s. The recognition system has essentially the same rate (5%) as a simulation of the network with 32-b floating-point precision.