Universiti Teknologi Malaysia Institutional Repository

A connectionist system approach for learning logic programs

Siti Mariam, Shamsuddin and M. H., Mashinchi (2008) A connectionist system approach for learning logic programs. AICCSA 08 - 6th IEEE/ACS International Conference on Computer Systems and Applications . pp. 852-855.

[img]
Preview
PDF - Published Version
252Kb

Official URL: http://dx.doi.org/10.1109/AICCSA.2008.4493628

Abstract

In this paper, we show that temporal logic can be learnt effectively by a connectionist system. In contrast with other connectionist approaches in this context, we focus more on learning rather than knowledge representation. In order to learn from temporal logic values, the paper proposes a general three-layer connectionist system regardless of the number of logic rules, a condition which must have been satisfied in previous approaches. A mapping function is proposed to convert logic rules to the proper connectionist system's inputs. Then a simulation study is carried out for muddy children puzzle. The results of the study suggest that an agent embedded with a connectionist system can learn temporal logic efficiently. It is observed that the connectionist system can increase its performance and make fewer mistakes while encountering with more produced cases of given logical rules

Item Type:Article
Additional Information:ISBN: 978-1-4244-1967-8
Uncontrolled Keywords:connectionist system, logic programs
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions:Computer Science and Information System (Formerly known)
ID Code:9921
Deposited By: Siti Najwa Hanim Kamarulzaman
Deposited On:22 Jun 2010 04:12
Last Modified:25 Jun 2010 05:02

Repository Staff Only: item control page