A Caltech Library Service

High-capacity exponential associative memories

Chiueh, Tzi-Dar and Goodman, Rodney M. (1988) High-capacity exponential associative memories. In: IEEE 1988 International Conference on Neural Networks. Vol.1. IEEE , Piscataway, NJ , pp. 153-160.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


A generalized associative memory model with potentially high capacity is presented. A memory of this kind with M stored vectors of length N, can be implemented with M nonlinear neurons, N ordinary thresholding neurons, and 2MN binary synapses. It is shown that special cases of this model include the Hopfield and high-order correlation memories. A special case of the model, based on a neuron which can implement the subthreshold region, is presented. The authors analyze the capacity of this exponentially associative memory and show that it scales exponentially with N. In any practical realization, however, the dynamic range of the exponentiators is constrained. They show that the capacity for networks with fixed dynamic range exponential circuits is proportional to the dynamic range.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1988 IEEE.
Record Number:CaltechAUTHORS:20190314-130609692
Persistent URL:
Official Citation:Chiueh Tzi-Dar and Goodman, "High-capacity exponential associative memories," IEEE 1988 International Conference on Neural Networks, San Diego, CA, USA, 1988, pp. 153-160 vol.1. doi: 10.1109/ICNN.1988.23843
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:93823
Deposited By: George Porter
Deposited On:14 Mar 2019 21:21
Last Modified:16 Nov 2021 17:00

Repository Staff Only: item control page