Application of the population learning algorithm to training feed-forward ANN

• Autorzy: Czarnowski, I. , Jędrzejowicz, P.
• Języki publikacji: EN

Abstrakty

EN

The chapter investigates the application of the new metaheuristic called the population learning algorithm (PLA) to training feed-forward artificial neural networks. This chapter introduces the population learning algorithm and proposes several implementations developed with a view to training several benchmark neural networks. The approach is compared with two alternative methods of training: quick propagation and genetic programming. Computer experiments show the high effectiveness and good quality of the suggested approach.

Słowa kluczowe

PL

metaheurystyka; algorytm uczenia populacji; PLA; sztuczne sieci neuronowe; ANN

EN

metaheuristics; population learning algorithm; PLA; artificial neural networks; ANN

• Czasopismo: Prace Naukowe Politechniki Warszawskiej. Elektronika
• Rocznik: 2002
• Tom: z. 139
• Strony: 147--161
• Opis fizyczny: Bibliogr. 11 poz., tab., rys., wykr.

Twórcy

autor

Czarnowski, I.

• Department of Information Systems, Gdynia Maritime Academy, Morska 83, 81-225 Gdynia,

autor

Jędrzejowicz, P.

• Department of Information Systems, Gdynia Maritime Academy, Morska 83, 81-225 Gdynia,

Bibliografia

• 1. Gorman R.P., Sejnowski T.J.: Analysis of hiden units in a layered network trained to classify sonar targets, Neural Networks 1, 1988, 75-89. http://yoga.cis.temple.edu:8080/cgi-bin/asprin.
• 2. Hertz J., Krogh A., Palmer R.G.: Introduction to the theory of neural computing. Addison-Wesley, 1992.
• 3. Hopfield J.J., Tank D.W.: Neural Computations of Decision in Optimisation Problems, Biological Cybernetics, vol. 52, 1985, 141-152.
• 4. Jędrzejowicz P.: Social Learning Algorithm as a tool for Solving Some Difficult Scheduling Problems, Foundation of Computing and Decision Sciences, vol. 24, 1999, 51-66.
• 5. Koza J.R., Rice J.P.: Genetic Generation of both the Weights and Architecture for a Neural Network, JCNN’91, Seattle, WA, USA.
• 6. Maniezo V.: Genetic Evolution of the Topology and Weight Distribution of Neural Networks. IEEE Transactions on Neural Networks, vol. 1, no 5, 1994, 369.
• 7. Michalewicz Z.: Genetic algorithms + data structures = evolution programs, Springers-Verlag, 1992.
• 8. Munakata T.: Fundamentals of the new artificial intelligence, Springers-Verlag, New York, 1998.
• 9. Rutkowska D., Piliński M.,. Rutkowski L.: Sieci Neuronowe, algorytmy genetyczne i systemy rozmyte, Wydawnictwo Naukowe PWN, Warszawa, 1997.
• 10. Whitley D.: Genetic algorithm and neural networks, genetic algorithm and computer science, in: g. Winter, J. Periaux, M. Galan, P. Guesta (eds.), John Wiley 1995, 203-216.
• 11. Shang Yi, Wah B.W.: A optimization method for neutral network training, Proc. IEEE Conf. on Neural Networks, (planary Panel and Special Sessions), 1996, 7-11.