A connectionist system approach for learning logic programs

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...

Full description

Bibliographic Details
Main Authors: Shamsuddin, Siti Mariam, Mashinchi, M. H.
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers 2008
Subjects:
Online Access:http://eprints.utm.my/9921/1/SitiMaryamShamsuddin2008_AConnectionistSystemApproachforLearning.pdf
_version_ 1796854606335049728
author Shamsuddin, Siti Mariam
Mashinchi, M. H.
author_facet Shamsuddin, Siti Mariam
Mashinchi, M. H.
author_sort Shamsuddin, Siti Mariam
collection ePrints
description 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
first_indexed 2024-03-05T18:16:34Z
format Article
id utm.eprints-9921
institution Universiti Teknologi Malaysia - ePrints
language English
last_indexed 2024-03-05T18:16:34Z
publishDate 2008
publisher Institute of Electrical and Electronics Engineers
record_format dspace
spelling utm.eprints-99212017-10-23T11:17:49Z http://eprints.utm.my/9921/ A connectionist system approach for learning logic programs Shamsuddin, Siti Mariam Mashinchi, M. H. QA75 Electronic computers. Computer science QA76 Computer software 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 Institute of Electrical and Electronics Engineers 2008 Article PeerReviewed application/pdf en http://eprints.utm.my/9921/1/SitiMaryamShamsuddin2008_AConnectionistSystemApproachforLearning.pdf Shamsuddin, Siti Mariam and Mashinchi, M. H. (2008) A connectionist system approach for learning logic programs. AICCSA 08 - 6th IEEE/ACS International Conference on Computer Systems and Applications . pp. 852-855. http://dx.doi.org/10.1109/AICCSA.2008.4493628 doi:10.1109/AICCSA.2008.4493628
spellingShingle QA75 Electronic computers. Computer science
QA76 Computer software
Shamsuddin, Siti Mariam
Mashinchi, M. H.
A connectionist system approach for learning logic programs
title A connectionist system approach for learning logic programs
title_full A connectionist system approach for learning logic programs
title_fullStr A connectionist system approach for learning logic programs
title_full_unstemmed A connectionist system approach for learning logic programs
title_short A connectionist system approach for learning logic programs
title_sort connectionist system approach for learning logic programs
topic QA75 Electronic computers. Computer science
QA76 Computer software
url http://eprints.utm.my/9921/1/SitiMaryamShamsuddin2008_AConnectionistSystemApproachforLearning.pdf
work_keys_str_mv AT shamsuddinsitimariam aconnectionistsystemapproachforlearninglogicprograms
AT mashinchimh aconnectionistsystemapproachforlearninglogicprograms
AT shamsuddinsitimariam connectionistsystemapproachforlearninglogicprograms
AT mashinchimh connectionistsystemapproachforlearninglogicprograms