AGENT BASED MODELLING FOR NEW TECHNIQUE IN NEURO SYMBOLIC INTEGRATION
DOI:
https://doi.org/10.20319/mijst.2017.32.445454Keywords:
Neuro-Symbolic, Logic Programming, Hopfield, Activation Function, Agent Based ModellingAbstract
Logic program and neural networks are two important aspects in artificial intelligence. This paper 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 new learning rule based Activation Function was derived to accelerate the performance of doing logic programming in Hopfield Neural Network (HNN). This paper also shows focused on agent based modelling for presenting performance of doing logic programming in Hopfield network using new activation function. The effects of the activation function are analyzed mathematically and compared with the existing method. Computer simulations are carried out by using NETLOGO 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.
References
Hopfield, J.J. (1982). Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings. Natl. Acad. Sci. USA. , 79(8), 2554-2558.
Hopfield, J.J.(1984). Neurons with Graded Response Have Collective Computational Properties like Those of Two-State Neurons. Proceeding. Natl. Acad. Sci.USA, 81(10),3088- 3092.
Hopfield, J.J. and Tank, D.W.(1985). Neural Computation of Decisions in Optimization Problems. Biol. Cyber, 52, 141-152.
Kasihmuddin, B. M., Shareduwan, M., Mansor, B., Asyraf, M., & Sathasivam, S. (2016a). Hybrid Genetic Algorithm in the Hopfield Network for Logic Satisfiabiality Problem. Journal of Science and Technology, Pertanika, 25(1), 139-152.
Kasihmuddin, B. M., Shareduwan, M., Mansor, B., Asyraf, M., & Sathasivam, S. (2016b). Genetic Algorithm for Restricted Maximum k-Satisfiability in the Hopfield Network. International Journal of Interactive Multimedia & Artificial Intelligence, 4(2), 52-60.
Mansor, M. A., Sathasivam, S., Salleh, S., Aris, N., Bahar, A., Zainuddin, Z. M., Maan, N., Lee, M. H., Ahmad, T., & Yusof, Y. M. (2016). Performance analysis of activation function in higher order logic programming. In AIP Conference Proceedings, volume 1750, page 030007. AIP Publishing. https://doi.org/10.1063/1.4954543
Saratha Sathasivam. (2015). Acceleration Technique for Neuro Symbolic Integration. Applied Mathematical Sciences, 9, 409-417.
Sathasivam, S & Pei Fen, N. (2013). Developing Agent Based Modeling for Doing Logic Programming in Hopfield Network, Applied Mathematical Sciences, 7 (1), 23-35.
Wan Abdullah, W.A.T. Logic Programming on a Neural Network. (1992). Int .J. Intelligent Sys,7, 513-519.
Wan Abdullah, W.A.T.(1993). The Logic of Neural Networks. Phys. Lett. A., 176., 202-206. https://doi.org/10.1016/0375-9601(93)91035-4
Zeng, X. & Martinez, R. (1999). A new activation function in the Hopfield Network for Solving Optimization Problems. Proceedings of Fourth International Conference On Artificial Neural Networks and Genetic Algorithms, Slovenia, 73-77.
Downloads
Published
How to Cite
Issue
Section
License
Copyright of Published Articles
Author(s) retain the article copyright and publishing rights without any restrictions.
All published work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
