A comparison of two sigmoidal-type activation functions in video game controller evolution

Tan, Tse Guan and Teo, Jason Tze Wi and Patricia Anthony, (2011) A comparison of two sigmoidal-type activation functions in video game controller evolution. In: 2011 IEEE Conference on Sustainable Utilization Development in Engineering and Technology, STUDENT 2011;Semenyih;20 October 2011through21 October 2011, 20-21 October 2011, Semenyih, Kuala Lumpur, Malaysia.

Full text not available from this repository.

Abstract

This paper presents an empirical comparison of two sigmoidal-type activation functions in evolutionary artificial neural network models. They are the log-sigmoid and hyperbolic tangent sigmoid activation functions which were investigated in order for evolving neural network controllers to play a classic video game. A Hill-Climbing Neural Network (HillClimbNet) was developed using the hill-climbing method together with a feedforward neural network to automatically create an intelligent controller that can play the screen-capture of Ms. Pac-man arcade game. The experimental results showed that that the HillClimbNet with log-sigmoid outperforms the HillClimbNet with hyperbolic tangent sigmoid when used in the hidden and output layers of the network when the agent plays the game.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: Feed-forward artificial neural network, Hill-climbing, Hyperbolic tangent sigmoid, Log-sigmoid, ms. pac-man
Subjects: ?? TK7800-8360 ??
Q Science > QA Mathematics > QA76 Computer software
Depositing User: Unnamed user with email storage.bpmlib@ums.edu.my
Date Deposited: 30 Apr 2012 08:32
Last Modified: 08 Sep 2014 08:13
URI: http://eprints.ums.edu.my/id/eprint/4052

Actions (login required)

View Item View Item

Browse Repository
Collection
   Articles
   Book
   Speeches
   Thesis
   UMS News
Search
Quick Search

   Latest Repository

Link to other Malaysia University Institutional Repository

Malaysia University Institutional Repository