Agent Based Modelling For New Technique In Neuro Symbolic Integration

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.

[img]
Preview
 PDF - Published Version
Download (814kB) | Preview

Abstract

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.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: neuro-symbolic, logic programming, Hopfield, activation function
Subjects: Q Science > QA Mathematics > QA1-939 Mathematics
Divisions: Pusat Pengajian Sains Matematik (School of Mathematical Sciences) > Conference or Workshop Item
Depositing User: Administrator Automasi
Date Deposited: 27 Jul 2017 04:44
Last Modified: 27 Jul 2017 04:44
URI: http://eprints.usm.my/id/eprint/35877

Actions (login required)

View Item View Item
USM Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.
Share