Simultaneous optimization of neural network function and architecture algorithm

Simultaneous optimization of neural network function and architecture algorithm

0.00 Avg rating0 Votes
Article ID: iaor20043295
Country: Netherlands
Volume: 36
Issue: 3
Start Page Number: 283
End Page Number: 296
Publication Date: Jan 2004
Journal: Decision Support Systems
Authors: , ,
Keywords: genetic algorithms
Abstract:

A major limitation to current artificial neural network research is the inability to adequately identify unnecessary weights in the solution. If a method were found that would allow unnecessary weights to be identified, decision-makers would gain crucial information about the problem at hand as well as benefit by having a network that was more effective and efficient. The Neural Network Simultaneous Optimization Algorithm (NNSOA) is proposed for supervised training in multilayer feedforward neural networks. We demonstrate with Monte Carlo studies that the NNSOA can be used to obtain both a global solution and simultaneously identify a parsimonious network structure.

Reviews

Required fields are marked *. Your email address will not be published.