An Analog Neural Network Processor with Programmable Topology

Bernhard E. Boser, Eduard Säckinger, Jane Bromley, Yann Le Cun, Lawrence D. Jacket

Research output: Contribution to journalArticlepeer-review


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 is evaluated in 1 ms.

Original languageEnglish (US)
Pages (from-to)2017-2025
Number of pages9
JournalIEEE Journal of Solid-State Circuits
Issue number12
StatePublished - Dec 1991

ASJC Scopus subject areas

  • Electrical and Electronic Engineering


Dive into the research topics of 'An Analog Neural Network Processor with Programmable Topology'. Together they form a unique fingerprint.

Cite this