Neural network training and simulation using a multidimensional optimization system

International Journal of Computer Mathematics

Volumn 67, Issue 1-2, 1998, Pages 33-46

  Likas, A ^a   Karras, D A ^a   Lagaris, I E ^a  

^a UNIVERSITY OF IOANNINA   (Greece)

Author keywords

Merlin; Neural network simulation; Template; Training strategy

Indexed keywords

COST FUNCTIONS; NEURAL NETWORKS; COMPUTER SIMULATION; COMPUTER SOFTWARE; LEARNING SYSTEMS; OPTIMIZATION; PROBLEM SOLVING;

MERLIN; MINIMIZATION PROCEDURES; MULTIDIMENSIONAL OPTIMIZATION; NEURAL NETWORK SIMULATIONS; NEURAL NETWORK TRAINING; OPTIMIZATION SOFTWARE; TEMPLATE; TRAINING STRATEGY;

COMPUTER SOFTWARE; NEURAL NETWORKS;

MULTIDIMENSIONAL OPTIMIZATION SYSTEM; TRAINING STRATEGY;

EID: 0031653036     PISSN: 00207160     EISSN: None     Source Type: Journal    
DOI: 10.1080/00207169808804651     Document Type: Article

References (19)

1. Evangelakis, G. A., Rizos, J. P., Lagaris, I. E. and Demetropoulos. I. N. (1987). Merlin - Portable System for Multidimensional Minimization, Computer Physics Communications, 46, pp. 402-412.
2. Papageorgiou, D G., Chassapis, C. S. and Lagaris, I. E. (1989). MERLIN-2.0 - Enhanced and programmable version. Computer Physics Communications, 52, 241-247.
3. Chassapis, C. S., Papageorgiou, D. G. and Lagaris, I. E. (1989). MCL - Optimization Oriented Programming Language, Computer Physics Communications, 52, pp. 223-239.
4. Neider, J. A. and Mead, R. (1965). A Simplex Method for Function Minimization, Computer Journal, 7, pp. 308-313.
5. Fletcher, R. and Reeves, C. M. (1964). Function Minimization by Conjugate Gradients, Computer Journal, 7, pp. 149-154.
6. Polak, E. and Ribiere, G. (1969). Note sur la convergence de methodes de directions conjugees Revue, Fr. Inf. Rech. Oper., 16-R1, pp. 35-43.
7. Khoda, K. M., Liu, Y. and Storey, C. (1992). Generalized Polak-Ribiere Algorithm, J. Of Optimization Theory and Applications, 75, pp. 345-354.
8. Fletcher, R. and Powell, M. J. D. (1963). A rapidly convergent descent method for minimization. Computer Journal, 6, pp. 163-168.
9. Fletcher, R. (1970). A new approach to variable metric algorithms, Computer Journal, 13, pp. 317-322.
10. More, J. (1977). The Leveberg-Marquardt Algorithm: Implementation and Theory, Lecture Notes in Mathematics, 630, pp. 105-116, Springer.
11. Anderson, C. W. (1989). Learning to Control an Inverted Pendulum Using Neural Networks, IEEE Control Systems Magazine, 9(3), pp. 31-37.
12. Haykin, S. (1994). A Comprehensive Foundation, Macmillan Publishing Company.
13. Lin, C.-J. and Lin, C.-T. (1996). Reinforcement Learning for an ART-Based Fuzzy Adaptive Learning Control Network, IEEE Trans. On Neural Networks, 7(3), pp. 709-731.
14. Prechelt, L. (1994). PROBEN 1: A set of Neural Network Benchmark Problems and Benchmarking Rules, Tech. Report 21/94, September 30, 1994, Fakultat fur Informatik, Universitat Karlshruhe, Germany.
15. Whitley, D., Dominic, S., Das, R. and Anderson, C. W. (1993). Genetic Reinforcement Learning for Neurocontrol Problems, Machine Learning 13, pp. 259-284.
16. Kohonen, T. (1989). Self-Organization and Associative Memory 3rd ed. Berlin: Springer Verlag.
17. Anderson, E. (1935). The IRISes of the Gapse Peninsula, Bull. Amer. IRIS Soc., 59, pp. 381-406.
18. Hathaway, R. J. (1995). Optimization of Clustering Criteria by Reformulation, IEEE Trans. On Fuzzy Syztems, 3(2), pp. 241-245.
19. Karayiannis, N., Bezdek, J. C., Pal, N. R., Hathaway, R. J. and Pai, P. (1996). Repairs to GLVQ: A New Family of Competitive Learning Schemes IEEE Trans. On Neural Networks, 7(5), pp. 1062-1071.