New globally convergent training scheme based on the resilient propagation algorithm

Neurocomputing

Volumn 64, Issue 1-4 SPEC. ISS., 2005, Pages 253-270

  Anastasiadis, Aristoklis D ^a   Magoulas, George D ^a   Vrahatis, Michael N ^b  

^a UNIVERSITY OF LONDON   (United Kingdom)

^b UPAIRC ^*  (Greece)

Author keywords

Batch learning; Convergence analysis; First order training algorithms; Global convergence property; IRprop; Rprop; Supervised learning

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; ITERATIVE METHODS;

CONVERGENCE ANALYSIS; LOCAL LEARNING RATES; RESILIENT PROPAGATION (RPROP) ALGORITHMS; TRAINING SCHEMES;

LEARNING SYSTEMS;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER PROGRAM; DATA BASE; HYPOTHESIS; INFORMATION PROCESSING; INFORMATION RETRIEVAL; INTERMETHOD COMPARISON; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; PRIORITY JOURNAL; PROBABILITY; QUALITY CONTROL; STANDARD; THYROID FUNCTION;

EID: 15844401040     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2004.11.016     Document Type: Article

References (28)

1. A.D. Anastasiadis, G.D. Magoulas, X. Liu, Classification of protein localisation patterns via supervised neural network learning, in: Proceedings of the Fifth Symposium on Intelligent Data Analysis (IDA-03), Berlin, Germany, August 2003, Lecture Notes in Computer Science, vol. 2810, Springer, Berlin, pp. 430-439.
2. R. Battiti First- and second-order methods for learning: Between steepest descent and Newton's method Neural Comput. 4 1992 141-166
3. F.R. Blattner G. Plunkett C.A. Bloch N.T. Perna V. Burland M. Riley J. Collado-Vides J.D. Glasner C.K. Rode G.F. Mayhew J. Gregor N.W. Davis H.A. Kirkpatrick M.A. Goeden D.J. Rose B. Mau Y. Shao The complete genome sequence of Escherichia coli K-12 Science 277 5331 1997 1453-1462
4. J.E. Dennis R.B. Schnabel Numerical Methods for Unconstrained Optimization and Nonlinear Equations 1996 SIAM Philadelphia
5. P.E. Gill W. Murray M.H. Wright Practical Optimization 1981 Academic Press New York
6. M.T. Hagan M.B. Menhaj Training feedforward networks with the Marquardt algorithm IEEE Trans. Neural Networks 5 1994 989-993
7. P. Horton, K. Nakai, Better prediction of protein cellular localization sites with the k nearest neighbors classifier, in: Proceedings of Intelligent Systems in Molecular Biology, 1997, pp. 368-383.
8. C. Igel M. Husken Empirical evaluation of the improved Rprop learning algorithms Neurocomputing 50 2003 105-123
9. P. Liang B. Labedan M. Riley Physiological genomics of Escherichia coli protein families Physiol. Genomics 9 1 2002 15-26
10. H. Lodish A. Berk S.L. Zipursky P. Matsudaira D. Baltimore J. Darnell Molecular Cell Biology fifth ed. 2003 Freeman New York
11. G.D. Magoulas M.N. Vrahatis G.S. Androulakis Effective back-propagation training with variable stepsize Neural Networks 10 1997 69-82
12. G.D. Magoulas M.N. Vrahatis G.S. Androulakis Improving the convergence of the backpropagation algorithm using learning rate adaptation methods Neural Comput. 11 1999 1769-1796
13. M.F. Moller A scaled conjugated gradient algorithm for fast supervised learning Neural Networks 6 1993 525-533
14. P.M. Murphy, D.W. Aha, UCI Repository of machine learning databases, University of California, Irvine, CA, 1994. http://www.ics.uci.edu/mlearn/MLRepository.html.
15. K. Nakai M. Kanehisa Expert system for predicting protein localization sites in gram-negative bacteria PROTEINS: Structure, Function, and Genetics 11 1991 95-110
16. K. Nakai M. Kanehisa A knowledge base for predicting protein localization sites in eukaryotic cells Genomics 14 1992 897-911
17. J. Nocedal, Theory of algorithms for unconstrained optimization, Acta Numer. (1992) 199-242.
18. L.M. Patnaik K. Rajan Target detection through image processing and resilient propagation algorithms Neurocomputing 35 1-4 2000 123-135
19. M. Pfister R. Rojas Speeding-up backpropagation - a comparison of orthogonal techniques in: Proceedings of the Joint Conference on Neural Networks Nagoya 1993 517-523
20. L. Prechelt, PROBEN1-A set of benchmarks and benchmarking rules for neural network training algorithms, Technical Report 21/94, Fakultät für Informatik, Universität Karlsruhe, 1994.
21. M. Riedmiller H. Braun A direct adaptive method for faster backpropagation learning: The RPROP algorithm in: Proceedings of the International Conference on Neural Networks San Francisco 1993 586-591
22. D.E. Rumelhart J.L. McClellend Parallel Distributed Processing: Explorations in the Microstructure of Cognition 1986 MIT Press Cambridge 318-362
23. N.K. Treadgold T.D. Gedeon Simulated annealing and weight decay in adaptive learning: The SARPROP algorithm IEEE Trans. Neural Networks 9 4 1998 662-668
24. D. Van Belle B. Andre A genomic view of yeast membrane transporters Curr. Opin. Cell Biol. 13 4 2001 389-398
25. M.N. Vrahatis G.S. Androulakis J.N. Lambrinos G.D. Magoulas A class of gradient unconstrained minimization algorithms with adaptive stepsize J. Comput. Appl. Math. 114 2 2000 367-386
26. M.N. Vrahatis G.D. Magoulas V.P. Plagianakos From linear to nonlinear iterative methods Appl. Numer. Math. 45 2003 59-77
27. P. Wolfe Convergence conditions for ascent methods SIAM Rev. 11 1969 226-235
28. P. Wolfe Convergence conditions for ascent methods. II: Some corrections SIAM Rev. 13 1971 185-188