A Caltech Library Service

A Novel Associative Memory Implemented Using Collective Computation

Sivilotti, Massimo and Emerling, Michael and Mead, Carver (1985) A Novel Associative Memory Implemented Using Collective Computation. In: 1985 Chapel Hill Conference on Very Large Scale Integration. Computer Science Press , Rockville, MD, pp. 329-342. ISBN 0881751030.

Full text is not posted in this repository.

Use this Persistent URL to link to this item:


A radically new type of associative memory, the ASSOCMEM, has been implemented in VLSI and tested. Analog circuit techniques are used to construct a network that evolves towards fully restored (digital) fixed-points that are the memories of the system. Association occurs on the whole source word, each bit of which may assume a continuous analog value. The network does not require the distinction of a search key from a data field in either the source or target words. A key may be dynamically defined by differentially weighting any subset of the source word. The key need not be exact; the system will evolve to the closest memory. In the case when the key is the whole input word, the system may be thought of as performing error correction.

Item Type:Book Section
Additional Information:© 1985 Computer Science Press. This research was funded by the System Development Foundation. One of us (MS) was also partially supported by the Natural Sciences and Engineering Research Council (NSERC) of Canada. The authors are indebted to Dr. John Hopfield, David Feinstein, and John Platt for many hours of stimulating discussions concerning the nature and properties of collective systems.
Funding AgencyGrant Number
System Development FoundationUNSPECIFIED
Natural Sciences and Engineering Research Council of Canada (NSERC)UNSPECIFIED
Record Number:CaltechAUTHORS:20150310-154028014
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:55689
Deposited On:11 Mar 2015 05:36
Last Modified:03 Oct 2019 08:07

Repository Staff Only: item control page