The Open UniversitySkip to content
 

An analog neural network processor with programmable topology

Boser, Bernhard E.; Säckinger, Eduard; Bromley, Jane M.; Le Cun, Yann and Jackel, Lawrence D. (1991). An analog neural network processor with programmable topology. IEEE Journal of Solid-State Circuits, 26(12) pp. 2017–2025.

Full text available as:
Full text not publicly available (Version of Record)
Due to publisher licensing restrictions, this file is not available for public download
Click here to request a copy from the OU Author.
DOI (Digital Object Identifier) Link: https://doi.org/10.1109/4.104196
Google Scholar: Look up in Google Scholar

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

Item Type: Journal Item
Copyright Holders: 1991 IEEE
ISSN: 0018-9200
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID: 35660
Depositing User: Jane M. Bromley
Date Deposited: 16 May 2013 10:19
Last Modified: 07 Dec 2018 13:38
URI: http://oro.open.ac.uk/id/eprint/35660
Share this page:

Metrics

Altmetrics from Altmetric

Citations from Dimensions

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU