Training of neural network using evolutionary computational techniques

Citation

Chong, Siang Yew (2003) Training of neural network using evolutionary computational techniques. Masters thesis, Multimedia University.

Full text not available from this repository.
Official URL: http://erep.mmu.edu.my/

Abstract

The primary goal of this research project is to study the feasibility of evolutionary computation in training neural networks through a game setting. The evolved neural networks is developed as an autonomous self-learning system, capable of learning to play the game of Othello without the need of preprogrammed expert knowledge. To facilitate this study, computer simulation is used as the main experimental method. This study is concerned especially with two particular aspects of intelligence -namely decision-making and learning- to be demonstrated by the evolved neural network. The decision-making capability is provided by the neural network, which is based specifically on a feedforward multiplayer perceptron model. Each neural network represents a particular Orthello-playing strategy.

Item Type: Thesis (Masters)
Additional Information: Call No.: QA76.87 .C46 2003
Uncontrolled Keywords: Neural networks (Computer science)
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 22 Aug 2024 05:03
Last Modified: 22 Aug 2024 05:03
URII: http://shdl.mmu.edu.my/id/eprint/12854

Downloads

Downloads per month over past year

View ItemEdit (login required)