Agent Based Modelling For New Technique In Neuro Symbolic Integration
This paper shows on developing agent based modelling for represent the performance of doing logic programming in Hopfield network by using a new activation function. The effects of the activation function on the performance of the neuro-symbolic integration are analyzed mathematically and compared w...
Saved in:
Main Authors: | , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://eprints.usm.my/35877/1/Saratha_Sathasivam_MUHA2.pdf http://eprints.usm.my/35877/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.usm.eprints.35877 |
---|---|
record_format |
eprints |
spelling |
my.usm.eprints.35877 http://eprints.usm.my/35877/ Agent Based Modelling For New Technique In Neuro Symbolic Integration Sathasivam, Saratha Velavan, Muraly QA1-939 Mathematics This paper shows on developing agent based modelling for represent the performance of doing logic programming in Hopfield network by using a new activation function. The effects of the activation function on the performance of the neuro-symbolic integration are analyzed mathematically and compared with the existing method. Computer simulations are carried out to validate the effectiveness on the new activation function. The resuls obtained showed that the new activation function outperform the existing method in doing logic programming in Hopfield network. The models developed by agent based modelling also support this theory. 2017 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.usm.my/35877/1/Saratha_Sathasivam_MUHA2.pdf Sathasivam, Saratha and Velavan, Muraly (2017) Agent Based Modelling For New Technique In Neuro Symbolic Integration. In: 16th International Conference on Researches in Science & Technology (ICRST), 14-15 July 2017, Bali, Indonesia. |
institution |
Universiti Sains Malaysia |
building |
Hamzah Sendut Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Sains Malaysia |
content_source |
USM Institutional Repository |
url_provider |
http://eprints.usm.my/ |
language |
English |
topic |
QA1-939 Mathematics |
spellingShingle |
QA1-939 Mathematics Sathasivam, Saratha Velavan, Muraly Agent Based Modelling For New Technique In Neuro Symbolic Integration |
description |
This paper shows on developing agent based modelling for represent the performance of doing logic programming in Hopfield network by using a new activation function. The effects of the activation function on the performance of the neuro-symbolic integration are analyzed mathematically and compared with the existing method. Computer simulations are carried out to validate the effectiveness on the new activation function. The resuls obtained showed that the new activation function outperform the existing method in doing logic programming in Hopfield network. The models developed by agent based modelling also support this theory. |
format |
Conference or Workshop Item |
author |
Sathasivam, Saratha Velavan, Muraly |
author_facet |
Sathasivam, Saratha Velavan, Muraly |
author_sort |
Sathasivam, Saratha |
title |
Agent Based Modelling For New Technique In Neuro Symbolic Integration |
title_short |
Agent Based Modelling For New Technique In Neuro Symbolic Integration |
title_full |
Agent Based Modelling For New Technique In Neuro Symbolic Integration |
title_fullStr |
Agent Based Modelling For New Technique In Neuro Symbolic Integration |
title_full_unstemmed |
Agent Based Modelling For New Technique In Neuro Symbolic Integration |
title_sort |
agent based modelling for new technique in neuro symbolic integration |
publishDate |
2017 |
url |
http://eprints.usm.my/35877/1/Saratha_Sathasivam_MUHA2.pdf http://eprints.usm.my/35877/ |
_version_ |
1643708622793867264 |
score |
13.187197 |