Hybrid Ant Colony Optimization For Two Satisfiability Programming In Hopfield Neural Network

Kho, Liew Ching (2019) Hybrid Ant Colony Optimization For Two Satisfiability Programming In Hopfield Neural Network. Masters thesis, Universiti Sains Malaysia.

[img]
Preview
PDF
Download (646kB) | Preview

Abstract

The representation of 2 Satisfiability problem or 2SAT is increasingly viewed as a significant logical rule in order to synthesize many real life applications. Although there were many researchers proposed the solution of 2SAT, little attention has been paid to the significance of the 2SAT logical rule itself. It can be hypothesized that 2SAT property can be used as a logical rule in the intelligent system. To verify this claim, 2 Satisfiability logic programming was embedded to Hopfield neural network (HNN) as a single unit. Learning in HNN will be inspired by Wan Abdullah method since the conventional Hebbian learning is inefficient when dealing with large number of constraints. As the number of 2SAT clauses increased, the efficiency and effectiveness of the learning phase in HNN deteriorates. Swarm intelligence metaheuristic algorithm has been introduced to reduce the learning complexity of the network. The newly proposed metaheuristic algorithm was enhanced ant colony optimization (ACO) algorithm.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > QA1 Mathematics (General)
Divisions: Pusat Pengajian Sains Matematik (School of Mathematical Sciences) > Thesis
Depositing User: Mr Hasmizar Mansor
Date Deposited: 23 Nov 2022 04:34
Last Modified: 23 Nov 2022 04:34
URI: http://eprints.usm.my/id/eprint/55729

Actions (login required)

View Item View Item
Share