Associative Memory Design via Path Embedding into a Graph

Authors:
Mehmet Kerem Mü/ezzinoğ/lu;Cü/neyt Gü/zeli
Affiliations:
Electrical and Computer Engineering Department, Lutz Hall 407, University of Louisville, Louisville 40292, KY, USA/ e-mail: mkerem@ieee.org;Electrical and Computer Engineering Department, Lutz Hall 407, University of Louisville, Louisville 40292, KY, USA
Venue:
Neural Processing Letters
Year:
2004

Citing 3
Cited 0

Linear programming and network flows (2nd ed.)

Linear programming and network flows (2nd ed.)
A two-level Hamming network for high performance associative memory

Neural Networks
An Analog VLSI Implementation of Hopfield's Neural Network

IEEE Micro

Quantified Score

Hi-index	0.00

Visualization

Abstract

A graph theoretical procedure for storing a set of n-dimensional binary vectors as asymptotically stable equilibrium points of a discrete Hopfield neural network is presented. The method gives an auto-associative memory which stores an arbitrary memory set completely. Spurious memories might occur only in a small neighborhood of the original memory vectors, so cause small errors.