A heuristic and its mathematical analogue within artificial neural network adaptation context

Title:

A heuristic and its mathematical analogue within artificial neural network adaptation context

Creator:

Serpen, Gursel

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:834da3d6-5285-4d8c-b0b7-378337952031
uuid:834da3d6-5285-4d8c-b0b7-378337952031

Subject:

Hopfield network, adaptation methods, heuristic methods, and gradient descent

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

This paper presents an observation on adaptation of Hopfield neural network dynamics configured as a relaxation-based search algorithm for static optimization. More specifically, two adaptation rules, one heuristically formulated and the second being gradient descent based, for updating constraint weighting coefficients of Hopfield neural network dynamics are discussed. Application of two adaptation rules for constraint weighting coefficients is shown to lead to an identical form for update equations. This finding suggests that the heuristically-formulated rule and the gradient descent based rule are analogues of each other. Accordingly, in the current context, common sense reasoning by a domain expert appears to possess a corresponding mathematical framework.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2005 Volume:15 | Number:2

Harvested from:

CDK

Metadata only:

false