Learning in feedforward layered networks: the tiling algorithm

作者: M Mezard , Jean-P Nadal

DOI: 10.1088/0305-4470/22/12/019

关键词: Feed forwardBoolean functionConvergence (routing)Order (ring theory)Numerical testsMathematicsLayer (object-oriented design)Algorithm

摘要: The authors propose a new algorithm which builds feedforward layered network in order to learn any Boolean function of N units. number layers and the hidden units each layer are not prescribed advance: they outputs algorithm. It is an for growth network, adds layers, inside layer, at will until convergence. convergence guaranteed numerical tests this strategy look promising.

参考文章(10)
Ben S. Wittner, John J. Hopfield, Sara A. Solla, Lawrence D. Jackel, John S. Denker, Daniel B. Schwartz, Richard E. Howard, Large Automatic Learning, Rule Extraction, and Generalization. Complex Systems. ,vol. 1, ,(1987)
P. Werbos, Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences Ph. D. dissertation, Harvard University. ,(1974)
T. J. Sejnowski, Parallel networks that learn to pronounce English text Complex Systems. ,vol. 1, pp. 145- 168 ,(1987)
Monte Carlo methods in statistical physics Monte Carlo methods in statistical physics. ,(1979) , 10.1007/978-3-642-82803-4
P Carnevali, S Patarnello, Exhaustive Thermodynamical Analysis of Boolean Learning Networks EPL. ,vol. 4, pp. 1199- 1204 ,(1987) , 10.1209/0295-5075/4/10/020
W Krauth, M Mezard, Learning algorithms with optimal stability in neural networks Journal of Physics A. ,vol. 20, ,(1987) , 10.1088/0305-4470/20/11/013
D.E. RUMELHART, G.E. HINTON, R.J. WILLIAMS, Learning internal representations by error propagation Neurocomputing: foundations of research. pp. 673- 695 ,(1988) , 10.1016/B978-1-4832-1446-7.50035-2
Frank Rosenblatt, Principles of neurodynamics ,(1962)
Ronny Meir, Eytan Domany, Tal Grossman, Learning by choice of internal representations Complex Systems. ,vol. 2, pp. 555- 575 ,(1988)
Monte Carlo Methods in Statistical Physics Monte Carlo Methods in Statistical Physics. Series: Topics in Current Physics. ,vol. 7, ,(1979) , 10.1007/978-3-642-96483-1