Energy landscape for Hopfield network programmed with program clauses

Authors:
Saratha Sathasivam
Affiliations:
University of Science Malaysia, Penang, Malaysia
Venue:
ACST '08 Proceedings of the Fourth IASTED International Conference on Advances in Computer Science and Technology
Year:
2008

Citing 5
Cited 0

CNF satisfiability test by counting and polynomial average time

SIAM Journal on Computing
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Handbook of Evolutionary Computation

Handbook of Evolutionary Computation
What does the Landscape of a Hopfield Associative Memory Look Like?

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
The computational complexity of N-K fitness functions

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show that the energy landscape of a Little-Hopfield neural network programmed with program clauses is rather flat. We argue that this should be so given the characteristics of program clauses and show through computer simulations that this is indeed so. We discuss satisfiability of program clauses with respect to logic programming in relation to this result.