Abstract
A neural network with 136000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network ship. The neural network chip is capable of processing 1000 characters per second. The recognition system has essentially the same error rate (5%) as a simulation of the network with 32-bit floating-point precision.
Original language | English (US) |
---|---|
Pages (from-to) | 498-505 |
Number of pages | 8 |
Journal | IEEE Transactions on Neural Networks |
Volume | 3 |
Issue number | 3 |
DOIs | |
State | Published - May 1992 |
ASJC Scopus subject areas
- Software
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence