Explorations of fitness landscapes of a Hopfield associative memory with random and evolutionary walks

Akira Imada, Keijiro Araki

Research output: Contribution to conferencePaperpeer-review

Abstract

We apply evolutionary computations to the Hopfield's neural network model of associative memory. In the model, some of the appropriate configurations of the synaptic weights give the network a function of associative memory. One of our goals is to obtain the distribution of these optimal configurations as the global optima in the synaptic weight space as well as the information of local optima created together. In other words, our aim is to know a geometry of fitness landscapes defined on weight space. As a step toward this goal, we concentrate in this paper mainly on the local optima. Hence, we use a walk by the Gaussian mutation to explore the fitness landscape, rather than more effective evolutionary walks, expecting its high probability to be trapped at the local optima.

Original languageEnglish
Pages364-369
Number of pages6
Publication statusPublished - Dec 1 1998
EventProceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98) - Adelaide, Aust
Duration: Apr 21 1998Apr 23 1998

Conference

ConferenceProceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98)
CityAdelaide, Aust
Period4/21/984/23/98

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Explorations of fitness landscapes of a Hopfield associative memory with random and evolutionary walks'. Together they form a unique fingerprint.

Cite this