Fixed points of the Abe formulation of Stochastic Hopfield Networks.

Abstract : The stability of stochastic Hopfield neural networks, in the Abe formulation, is studied. The aim is to determine whether the ability of the deterministic system to solve combinatorial optimization problems is preserved after the addition of random noise. In particular, the stochastic stability of the attractor set is analyzed: vertices, which are feasible points of the problem, should be stable, whereas interior points, which are unfeasible, should be unstable. Conditions on the noise intensity are stated, so that these properties are guaranteed. This theoretical investigation establishes the foundations for practical application of stochastic networks to combinatorial optimization.
Complete list of metadatas
Contributor : Marie Kratz <>
Submitted on : Monday, October 15, 2007 - 3:07:11 PM
Last modification on : Sunday, January 19, 2020 - 6:38:29 PM

Links full text




Marie Kratz, Miguel Atencia, Gonzalo Joya. Fixed points of the Abe formulation of Stochastic Hopfield Networks.. 17th ICANN, Sep 2007, Porto, Portugal. pp.599-608, ⟨10.1007/978-3-540-74690-4_61⟩. ⟨hal-00179444⟩



Record views