Sains Malaysiana 39(1)(2010): 115–118

 

Upgrading Logic Programming in Hopfield Network

(Mempertingkatkan Logik Program dalam Rangkaian Hopfield)

 

Saratha Sathasivam

School of Mathematical Sciences, Universiti Sains Malaysia

11800 USM, Penang, Malaysia

 

Received: 28 April 2009 / Accepted: 17 June 2009

 

ABSTRACT

 

The convergence property for doing logic programming in Hopfield network can be accelerated by using new relaxation method. This paper shows that the performance of the Hopfield network can be improved by using a relaxation rate to control the energy relaxation process. The capacity and performance of these networks is tested by using computer simulations. It was proven by computer simulations that the new approach provides good solutions.

 

Keywords: Energy relaxation; Little-Hopfield neural networks; program clauses

 

ABSTRAK

 

Kriteria penumpuan untuk melakukan program logik dalam rangkaian Hopfield dapat dipertingkatkan dengan menggunakan kaedah berehat yang baru. Dalam artikel ini ditunjukkan bahawa operasi rangkaian Hopfield dapat dipertingkatkan dengan menggunakan kadar rehat bagi mengawal proses relaksi tenaga. Saiz dan kadar operasi rangkaian ini di uji dengan menggunakan simulasi komputer. Dibuktikan melalui simulasi komputer kaedah baru memberikan penyelesaian yang baik.

 

Kata kunci: Klausa program; rangkaian Neural Little-Hopfield; santaian tenaga

 

REFERENCES

 

Altenberg, Lee. 1997. Handbook of Evolutionary Computation: Oxford University Press.

Haykin, S. 1999. Neural Network: A Comprehensive Foundation. New York: Macmillan.

Hopfield, J.J. 1985. Neural computation of decisions in optimization problems. Biol. Cybern. 52: 141-152.

Hopfield, J.J. 1982. Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci (USA) 79: 2554-2558.

Little, W.A. 1974. The Existence of persistent states in the brain. Math. Biosci 19: 101-120.

Saratha Sathasivam & Wan Abdullah, W.A.T. 2008a. Flatness of the energy landscapes of horn clauses. MATEMATIKA 23(2): 147-156.

Saratha Sathasivam & Wan Abdullah, W.A.T. 2008b. Logic Learning in the hopfield Networks. Modern Applied Science 2(3): 57-62.

Saratha Sathasivam. 2006. Logic Mining in Neural Networks. PhD Thesis: University of Malaya, Malaysia.

Wan Abdullah, W.A.T. 1992. Logic programming on a neural network. Int. J. Intelligent Sys. 7: 513-519.

Zeng, S & Martinez, T. 1999. Improving the performance of the Hopfield network by using a relaxation rate, Proc. Int. Conference on Neural Networks and Genetic Algorithms: 73-77.

 

*Corresponding author; email: saratha@cs.usm.my