Microscopic equations in rough energy landscape for neural networks

Advances in Neural Information Processing Systems

Volumn , Issue , 1997, Pages 302-308

  Wong, K Y Michael ^a  

^a HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

CONVENTIONAL ALGORITHMS; EXPONENTIAL DISTRIBUTIONS; LEARNING PROBLEM; LEARNING PROCESS; MACROSCOPIC PROPERTIES; MICROSCOPIC EQUATIONS; REPLICA SYMMETRY BREAKINGS; ROUGH ENERGY LANDSCAPES;

NEURAL NETWORKS;

EID: 84898956158     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. Anlauf, J.K., & Biehl, M. (1989) The AdaTron: an adaptive perceptron algorithm. Europhysics Letters 10(7):687-692.
2. Bouten, M., Schietse, J. & Van den Broeck, C. (1995) Gradient descent learning in perceptrons: A review of its possibilities. Physical Review E 52(2):1958-1967.
3. Gardner, E. & Derrida, B. (1988) Optimal storage properties of neural network models. Journal of Physics A: Mathematical and General 21(l):271-284.
4. Gerl, F. & Krey, U. (1995) A Kuhn-Tucker cavity method for generalization with applications to perceptrons with Ising and Potts neurons. Journal of Physics A: Mathematical and General 28(23):6501-6516.
5. Griniasty, M. (1993) "Cavity-approach" analysis of the neural-network learning problem. Physical Review E 47(6):4496-4513.
6. Mezard, M. (1989) The space of interactions in neural networks: Gardners computation with the cavity method. Journal of Physics A: Mathematical and General 22(12):2181-2190.
7. Mezard, M., Parisi, G. & Virasoro, M. (1987) Spin Glass Theory and Beyond. Singapore: World Scientific.
8. Nilsson, N.J. (1965) Learning Machines. New York: McGraw-Hill.
9. Thouless, D.J., Anderson, P.W. & Palmer, R.G. (1977) Solution of solvable model of a spin glass. Philosophical Magazine 35(3):593-601.
10. Watkin, T.L.H., Rau, A. & Biehl, M. (1993) The statistical mechanics of learning a rule. Review of Modern Physics 65(2):499-556.
11. Wong, K.Y.M. (1995a) Microscopic equations and stability conditions in optimal neural networks. Europhysics Letters 30(4):245-250.
12. Wong, K.Y.M. (1995b) The cavity method: Applications to learning and retrieval in neural networks. In J.-H. Oh, C. Kwon and S. Cho (eds.), Neural Networks: The Statistical Mechanics Perspective, pp. 175-190. Singapore: World Scientific.