Solving local minima problem with large number of hidden nodes on two-layered feed-forward artificial neural networks

Neurocomputing

Volumn 71, Issue 16-18, 2008, Pages 3640-3643

  Choi, Bumghi ^a   Lee, Ju Hong ^a   Kim, Deok Hwan ^a  

^a Inha University   (South Korea)

Author keywords

Backpropagation; Hidden nodes; Local minima; Separate learning; Target values

Indexed keywords

BACKPROPAGATION; BACKPROPAGATION ALGORITHMS; BENCHMARKING; LEARNING ALGORITHMS; LEARNING SYSTEMS; OPTIMAL CONTROL SYSTEMS; PROBLEM SOLVING;

APPLICATIONS.; ARTIFICIAL NEURAL NETWORKS; BENCHMARK PROBLEMS; GRADIENT DESCENT ALGORITHMS; HIDDEN NODES; LOCAL MINIMA; LOCAL MINIMA PROBLEMS; SEPARATE LEARNING; TARGET VALUES;

NEURAL NETWORKS;

ARTIFICIAL NEURAL NETWORK; BREAST CANCER; COMPUTER SIMULATION; CONFERENCE PAPER; LEARNING ALGORITHM; MATHEMATICAL ANALYSIS; PRIORITY JOURNAL; PROBLEM SOLVING; VALIDITY;

EID: 56549091450     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2008.04.004     Document Type: Conference Paper

References (12)

1. G. Bilbro Fast stochastic global optimisation IEEE Trans. Syst. Man Cybern. 24 1994 684 689
2. B.C. Cetin, J.W. Burdick, J. Barhen, Global descent replaces gradient descent to avoid local minima problem in learning with ANN, in: Proceedings of the IEEE Conference on NN, vol. 2, 28 March-1 April 1993, pp. 836-842.
3. R. Hont P. Padalos Handbook of Global Optimization 1995 Kluwer Dordrecht
4. W. Huyer, and A. Neumaier Global optimization by multilevel coordinate search J. Global Optim. 14 1999 331 335
5. D. Jones, C. Perttunen, and B. Stuckman Lipschitzian optimization without the Lipschitz constant J. Optim. Theory Appl. 79 1993 157 181
6. I.N. Jordanov, T.A. Rafik, Local minima free network learning, in: Second IEEE International Conference on Intelligent Systems, vol. 1, 22-24 June 2004, pp. 34-39.
7. O.L. Mangasarian, and W.H. Wolberg Cancer diagnosis via linear programming SIAM News 23 5 1990 1 & 18
8. P. Plagianakos, G.D. Magoulas, and M. Vrahatis Deterministic non-monotone strategies for the effective training of multilayer perceptrons IEEE Trans. Neural Networks 13 6 2002 1268 1284
9. A. Tom, and S. Vitanen Topographical global optimization using pre-sampled points J. Global Optim. 5 1994 267 276
10. N.K. Treadgold, and T.D. Gedeon. Simulaed annealing and weight decay in adaptive learning: the SARPRO algorithm IEEE Trans. Neural Networks 9 1998 662 668
11. M. Vrahatis, G. Androulakis, J. Lambrinos, and G. Magoulas A class of gradient unconstrained minimization stepsize J. Comput. Appl. Math. 114 2000 367 386
12. X.H. Yu, and G.A. Chen On the local minima free condition of backpropagation learning IEEE Trans. Neural Networks 6 5 1995 1300 1303