Improving decision effectiveness of artificial neural networks: a modified genetic algorithm approach

Improving decision effectiveness of artificial neural networks: a modified genetic algorithm approach

0.00 Avg rating0 Votes
Article ID: iaor2009632
Country: United States
Volume: 34
Issue: 3
Start Page Number: 421
End Page Number: 442
Publication Date: Jul 2004
Journal: Decision Sciences
Authors: , ,
Keywords: heuristics: genetic algorithms, artificial intelligence: decision support, decision theory
Abstract:

This study proposes the use of a modified genetic algorithm (MGA), a global search technique, as a training method to improve generalizability and to identify relevant inputs in a neural network (NN) model. Generalizability refers to the NN model's ability to perform well on exemplars (observations) that were not used during training (out-of-sample); improved generalizability enhances NN's acceptability as a valid decision-support tool. The MGA improves generalizability by setting unnecessary weights (or connections) to zero and by eliminating these weights.

Reviews

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 Your email address will not be published.