Logo image
Nonpositive Hopfield Networks in Error Correcting Coding Applications
Conference proceeding

Nonpositive Hopfield Networks in Error Correcting Coding Applications

Yash Shrivastava, Soura Dasgupta and S.M Reddy
1993 American Control Conference, pp.1433-1437
American Control Conference (San Francisco, California, 06/02/1993–06/04/1993)
06/1993
DOI: 10.23919/ACC.1993.4793107

View Online

Abstract

We consider a class of symmetric Hopfield Networks, with nonpositive synapses and zero thresholds and address a variety of design and analysis issues conected with Unidirectional Error Correcting Coding applications of this class. We show that this class is naturally suited to work in a unidirectional error environment We give a necessary and sufficient condition for a set of vectors to be storable in a Nonpositive Network. We propose a simple word storage algorithm, which is amenable to on line implementation, and guarantees storage of all storage compatible words. We show that the storage algorithm creates a maximally fault tolerant network which is free from spurious stationary points, whenever that freedom is possible. We also give a word forgetting algorithm; a tight, deterministic bound on the storage capacity, and give conditions under which the network created by our storage scheme tolerates a given number of arbitrary physical faults.
Error correction Error correction codes Fault tolerance Hopfield neural networks Light sources Neural networks Sufficient conditions Symmetric matrices Tellurium Upper bound

Details

Metrics

19 Record Views
Logo image