Mutual learning using nonlinear perceptron

• Autorzy: Saitoh D. , Hara K.

Identyfikatory

DOI

10.1515/jaiscr-2015-0020

• Języki publikacji: EN

Abstrakty

EN

We propose a mutual learning method using nonlinear perceptron within the framework of online learning and have analyzed its validity using computer simulations. Mutual learning involving three or more students is fundamentally different from the two-student case with regard to variety when selecting a student to act as the teacher. The proposed method consists of two learning steps: first, multiple students learn independently from a teacher, and second, the students learn from others through mutual learning. Results showed that the mean squared error could be improved even if the teacher had not taken part in the mutual learning.

Słowa kluczowe

EN

mutual learning; nonlinear perceptron method; squared error; student; teacher; uczenie się wzajemne; student; nauczyciel

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2015
• Tom: Vol. 5, No. 1
• Strony: 71--77
• Opis fizyczny: Bibliogr. 8 poz., rys.

Twórcy

autor

Saitoh D.

• Graduate School of Industrial Technology, Nihon University 1-2-1 Izumi-cho, Narashino, Chiba, Japan 275-8575

autor

Hara K.

• College of Industrial Technology, Nihon University 1-2-1 Izumi-cho, Narashino, Chiba, Japan 275-8575

Bibliografia

• [1] E. Klein, R. Mislovaty, I. Kanter, A. Ruttor, and W. Kinzel, ” Synchronization of neural networks by mutual learning and its application to cryptography”, in Advance Neural Information Processing System, 17 (MIT Press, Cambridge, MA, 2005).
• [2] R. Metzler, W. Kinzel, and I. Kanter, ”Interacting neural networks”, Physical Review E 62, 2, (2000) 2555.
• [3] R. Mislovaty, E. Klein, I. Kanter, and W. Kinzel, ”Public Channel Cryptography by Synchronization of Neural Networks and Chaotic Maps”, Physical Review Letters, 91 (2003) 118701.
• [4] D. Saad (Ed.), Online Learning in Neural Networks, (Cambridge University Press, Cambridge, UK., 1998).
• [5] A. Krogh and P. Sollich, ” Statistical mechanics of ensemble learning”, Physical Review E, 55, 1 (1997) 811.
• [6] R. Beale and T. Jackson, Neural Computing: An Introduction, (Institution of Physic Publishing, 1990).
• [7] K. Hara, Y. Nakayama, S. Miyoshi, and M. Okada, ”Statistical Mechanics of On-Line Mutual Learning with Many Linear Perceptrons”, Journal of the Physical Society of Japan. 78 (2009) 114001.
• [8] K. Hara, K. Katahira, K. Okanoya, and M. Okada, ”Statistical Mechanics of Node-Perturbation Learning for Nonlinear Perceptron”, Jounal of the Physical Society of Japan. 82 (2013) 054001.