Global dynamics in neuro symbolic integration using energy minimization in mean field theory

Master of Science in Applied Mathematics

Saved in:

Bibliographic Details
Main Author:	Muraly Velavan, Doraisamy
Other Authors:	Zainor Ridzuan, Yahya. Dr.
Format:	Thesis
Language:	English
Published:	Universiti Malaysia Perlis (UniMAP) 2017
Subjects:	Logic programming Neural networks (Computer science) Mean Field Theory (MFT)
Online Access:	http://dspace.unimap.edu.my:80/xmlui/handle/123456789/77974
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Universiti Malaysia Perlis
Language:	English

id	my.unimap-77974
record_format	dspace
spelling	my.unimap-779742023-03-06T00:51:32Z Global dynamics in neuro symbolic integration using energy minimization in mean field theory Muraly Velavan, Doraisamy Zainor Ridzuan, Yahya. Dr. Logic programming Neural networks (Computer science) Mean Field Theory (MFT) Master of Science in Applied Mathematics Logic program and neural networks are two important aspects in artificial intelligence. This thesis is part of an endeavour towards neural networks and logic programming integration. The goal in performing logic programming based on the energy minimization scheme is to achieve the best ratio of global minimum. However, there is no guarantee to find the best minimum in the network. To achieve this, a learning algorithm based on the Boltzmann Machine (BM) concept and Hyperbolic Tangent Activation Function (HTAF) was derived to accelerate the performance of doing logic programming in Hopfield Neural Network (HNN) by using Mean Field Theory (MFT). Logic programming for lower order (up to third order clauses) and higher order clauses (up to eight order clauses) have been developed for MFT. The performance of this method is compared with the existing methods of doing logic programming in HNN (BM and HTAF). The global minima ratio, hamming distances and computational time were used to measure the effectiveness of the proposed method. Then, Agent Based Models (ABM) were developed by using Netlogo. ABM can allow rapid development of models, easy addition of features and a user-friendly handling and coding. Later the developed models are tested by using real life and simulated data sets. The simulation results obtain agreed with the proposed learning algorithm. The performance of doing logic programming using MFT proved to be better than the BM and HTAF. 2017 2023-03-06T00:49:19Z 2023-03-06T00:49:19Z Thesis http://dspace.unimap.edu.my:80/xmlui/handle/123456789/77974 en Universiti Malaysia Perlis (UniMAP) Universiti Malaysia Perlis (UniMAP) Institute of Engineering Mathematics
institution	Universiti Malaysia Perlis
building	UniMAP Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaysia Perlis
content_source	UniMAP Library Digital Repository
url_provider	http://dspace.unimap.edu.my/
language	English
topic	Logic programming Neural networks (Computer science) Mean Field Theory (MFT)
spellingShingle	Logic programming Neural networks (Computer science) Mean Field Theory (MFT) Muraly Velavan, Doraisamy Global dynamics in neuro symbolic integration using energy minimization in mean field theory
description	Master of Science in Applied Mathematics
author2	Zainor Ridzuan, Yahya. Dr.
author_facet	Zainor Ridzuan, Yahya. Dr. Muraly Velavan, Doraisamy
format	Thesis
author	Muraly Velavan, Doraisamy
author_sort	Muraly Velavan, Doraisamy
title	Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_short	Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_full	Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_fullStr	Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_full_unstemmed	Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_sort	global dynamics in neuro symbolic integration using energy minimization in mean field theory
publisher	Universiti Malaysia Perlis (UniMAP)
publishDate	2017
url	http://dspace.unimap.edu.my:80/xmlui/handle/123456789/77974
_version_	1772813066169221120

Global dynamics in neuro symbolic integration using energy minimization in mean field theory

Similar Items