Energy Landscape for Hopfield Network Programmed with Program Clauses

S. Sathasivam (Malaysia)

Keywords

LittleHopfield neural networks, program clauses, energy landscape, satisfiability

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.

Important Links:



Go Back