Genetic-Tabu design of neural network controllers

Chiu, K. S. and Hunter, Andrew (1998) Genetic-Tabu design of neural network controllers. In: International Computer Symposium 1998, 17-19 December 1998, National Cheng Kung University, Taiwan.

Documents
GA-Tabu_Design_of_Neural_Network_Controllers.pdf
[img]
[Download]
Request a copy
[img] PDF
GA-Tabu_Design_of_Neural_Network_Controllers.pdf - Whole Document
Restricted to Repository staff only

2152Kb

Abstract

This paper discusses the use of GAs (Genetic Algorithms) and TS (Tabu Search) to design NNCs (Neural Network Controllers) for Real-time control of flows in sewerage networks. Genetic algorithms evolve the weights for Neural Networks Controllers. We apply a modified Tabu Search algorithm in a novel fashion, to select the most relevant training data, in order to reduce the training time.

The comparison between this approach and various fixed penstock control settings, and genetically-designed Neural Networks, is discussed. This paper reports experiments demonstrating that GAs are both effective and robust to design Neural Networks controllers in sewerage network control problems. To confirm whether the GA-Tabu training algorithm has statistically significant better performance than other data selecting algorithms, a t-test with a 5% signigicance level is examined. Use of the Tabu algorithm
reduces the training time without affecting the results.

Item Type:Conference or Workshop Item (Paper)
Additional Information:This paper discusses the use of GAs (Genetic Algorithms) and TS (Tabu Search) to design NNCs (Neural Network Controllers) for Real-time control of flows in sewerage networks. Genetic algorithms evolve the weights for Neural Networks Controllers. We apply a modified Tabu Search algorithm in a novel fashion, to select the most relevant training data, in order to reduce the training time. The comparison between this approach and various fixed penstock control settings, and genetically-designed Neural Networks, is discussed. This paper reports experiments demonstrating that GAs are both effective and robust to design Neural Networks controllers in sewerage network control problems. To confirm whether the GA-Tabu training algorithm has statistically significant better performance than other data selecting algorithms, a t-test with a 5% signigicance level is examined. Use of the Tabu algorithm reduces the training time without affecting the results.
Keywords:Tabu, neural networks, Genetic algorithms
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:2836
Deposited By: Rosaline Smith
Deposited On:09 Jul 2010 11:18
Last Modified:13 Mar 2013 08:41

Repository Staff Only: item control page