Abstract
Training of neural networks by local search such as gradient-based algorithms could be difficult. This calls for the development of alternative training algorithms such as evolutionary search. However, training by evolutionary search often requires long computation time. In this chapter, we investigate the possibilities of reducing the time taken by combining the efforts of local search and evolutionary search. There are a number of attempts to combine these search strategies, but not all of them are successful. This chapter provides a critical review of these attempts. Moreover, different approaches to combining evolutionary search and local search are compared. Experimental results indicate that while the Baldwinian and the two-phase approaches are inefficient in improving the evolution process for difficult problems, the Lamarckian approach is able to speed up the training process and to improve the solution quality. In this chapter, the strength and weakness of these approaches are illustrated, and the factors affecting their efficiency and applicability are discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ackley, D. H., Littman, M. L. (1992) Interactions between learning and evolution. In C. G. Langton, C. Taylor, J. D. Farmer, and S. Rasmussen, editors, Artificial Life 2, 487–509. Redwood City, CA: Addison-Wesley
Ackley, D. H., Littman, M. L. (1994) A case for Lamarckian evolution. In C. G. Langton, editor, Artificial Life 3, 3–10. Reading, MA: Addison-Wesley
Angeline, P. J., Saunders, G. M., Pollack, J. B. (1994) An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5(1):54–65
Back, T., Hammel, U., Schwefel, H.-P. (1997) Evolutionary computation: Comments on the history and current state. IEEE Transactions on Evolutionary Computation, 1(1):3–17
Baldwin, J. M. (1896) A new factor in evolution. American Naturalist, 30:441–451
Belew, R. K., McInerney, J., Schraudolph, N. N. (1992) Evolving networks: Using the genetic algorithm with connectionist learning. In C. G. Langton, C. Taylor, J. D. Farmer, and S. Rasmussen, editors, Artificial Life 2, 511–547. Redwood City, CA: Addison-Wesley
Bengio, Y., Simard, P., Frasconi, P. (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2): 157–166
Braun, H., Zagorski, P. (1994) ENZO-M — a hybrid approach for optimizing neural networks by evolution and learning. In Y. Davidor, H.-P. Schwefel, and R. Manner, editors, Parallel Problem Solving from Nature — PPSN III, 440–451. Berlin: Springer-Verlag
Chalmers, D. J. (1990) The evolution of learning: An experiment in genetic connectionism. In D. S. Touretzky, editor, Proceedings of the 1990 Connectionist Models Summer School, 81–90. San Mateo, CA: Morgan Kaufmann
Collins, R. J., Jefferson, D. R. (1991) Selection in massively parallel genetic algorithms. In Proceedings of the Fourth International Conference on Genetic Algorithms, 249–256
Crosher, D. (1993) The artificial evolution of a generalized class of adaptive processes. In AI’93 Workshop on Evolutionary Computation, 18–36
Dantzig, G. B. (1963) Linear Programming and Extensions. Princeton, NJ: Princeton University Press
Davidor, Y. (1991) A naturally occurring niche& species phenomenon: The model and first results. In Proceedings of the Fourth International Conference on Genetic Algorithms, 257–262
De Garis, H. (1991) GenNets: Genetically programmed neural networks — using the genetic algorithm to train neural nets whose inputs and/or outputs vary in time. In Proceedings of the IEEE International Joint Conference on Neural Networks, 1391–1396
Elman, J. L. (1988) Finding structure in time. Technical Report CRL 8801, Center for Research in Language, University of California, San Diego
Erkmen, I., Ozdogan, A. (1997) Short term load forecasting using genetically optimized neural network cascaded with a modified kohonen clustering process. In Proceedings of the IEEE International Symposium on Intelligent Control, 107–112
Fogel, D. B. (1994) An introduction to simulated evolutionary optimization. IEEE Transactions on Neural Networks, 5(1):3–14
Fogel, D. B. (1995) Evolutionary computation: toward a new philosophy of machine intelligence. Piscataway, NJ: IEEE Press
Fogel, D. B., Fogel, L. J., Porto, V. W. (1990) Evolving neural networks. Biological Cybernetics, 63:487–493
Fogel, L. J., Owens, A. J., Walsh, M. J. (1966) Artificial Intelligence Through Simulated Evolution. New York: Wiley
Fontanari, J. F., Meir, R. (1991) Evolving a learning algorithm for the binary perceptron. Network, 2(4):353–359
French, R. M., Messinger, A. (1994) Genes, phenes and the Baldwin effect: Learning and evolution in a simulated population. In A. B. Rodney and M. Pattie, editors, Artificial Life 4, 277–282. Cambridge, MA: MIT Press
Goldberg, D. E. (1989) Genetic Algorithms in Search, Optimization, and Machine Learning. Reading, MA: Addison-Wesley
Greenwood, G. W. (1997) Training partially recurrent neural networks using evolutionary strategies. IEEE Transactions on Speech Audio Processing, 5(2):192–194
Gruau, F., Whitley, D. (1993) Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect. Evolutionary Computation, 1(3):213–233
Hanes, M. D., Ahalt, S. C., Krishnamurthy, A. K. (1994) Acoustic-to-phonetic mapping using recurrent neural networks. IEEE Transactions on Neural Networks, 5(4):659–662
Harp, S. A., Samad, T., Guha, A. (1989) Towards the genetic synthesis of neural networks. In J. D. Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, 360–369. San Mateo, CA: Morgan Kaufmann
Harvey, I. (1997) Is there another new factor in evolution? Evolutionary Computation, 4(3):313–329
Hebb, D. O. (1949) The Organization of Behavior. New York: Wiley
Hinton, G. E., Nowlan, S. J. (1987) How learning can guide evolution. Complex Systems, 1:495–502
Hornik, K. (1990) Approximation capabilities of multilayer feedforward neural networks. Neural Networks, 4:251–257
Huang, W. M., Lippmann, R. P. (1988) Neural net and traditional classifiers. In D. Anderson, editor, Neural Information Processing Systems, 387–396. New York: American Institute of Physics
Ichimura, T., Takano, T., Tazaki, E. (1995) Reasoning and learning method for fuzzy rules using neural networks with adaptive structured genetic algorithm. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 3269–3274
Janson, D. J., Frenzel, J. F. (1992) Application of genetic algorithms to the training of higher order neural networks. Journal of Systems Engineering, 2(4):272–276
Janson, D. J., Frenzel, J. F. (1993) Training product unit neural networks with genetic algorithms. IEEE Expert, 8(5):26–33
Jordan, M. I. (1986) Attractor dynamics and parallelism in a connectionist sequential machine. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society, 531–546
Keesing, R., Stork, D. G. (1991) Evolution and learning in neural networks: The number and distribution of learning trial affect the rate of evolution. In R. P. Lippmann, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems 3, 804–810. San Mateo, CA: Morgan Kaufmann
Kim, H. B., Jung, S. H., Kim, T. G., Park, K. H. (1996) Fast learning method for back-propagation neural network by evolutionary adaptation of learning rates. Neurocomputating, 11(1):101–106
Kitano, H. (1990) Empirical studies on the speed of convergence of neural network training using genetic algorithms. In Proceedings of the Eighth National Conference on Artificial Intelligence, 789–795
Kolen, J. F., Pollack, J. B. (1990) Back propagation is sensitive to initial conditions. Complex Systems, 4:269–280
Korning, P. G. (1995) Training neural networks by means of genetic algorithms working on very long chromosomes. International Journal of Neural Systems, 6(3):299–316
Ku, K. W. C. (1999) On the Combination of Local and Evolutionary Search for Training Recurrent Neural Networks. PhD thesis, The Hong Kong Polytechnic University, Hong Kong
Ku, K. W. C., Mak, M. W. (1997) Exploring the effects of Lamarckian and Baldwinian learning in evolving recurrent neural networks. In Proceedings of the IEEE International Conference on Evolutionary Computation, 617–621
Ku, K. W. C., Mak, M. W. (1998) Empirical analysis of the factors that affect the Baldwin effect. In A. E. Eiben, T. Back, M. Schoenauer, and H.-P. Schwefel, editors, Parallel Problem Solving from Nature — PPSN V, 481–490. Berlin: Springer-Verlag
Ku, K. W. C., Mak, M. W., Siu, W. C. (2000) A study of the Lamarckian evolution of recurrent neural networks. IEEE Transactions on Evolutionary Computation, 4(1):31–42
Ku, K. W. C., Mak, M. W., Siu, W. C. (1999) Adding learning to cellular genetic algorithms for training recurrent neural networks. IEEE Transactions on Neural Networks, 10(2):239–252
Lee, S. W. (1996) Off-line recognition of totally unconstrained handwritten numerals using multilayer cluster neural network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(6):648–652
Lippmann, R. P. (1987) An introduction to computing with neural nets. IEEE Acoustics, Speech, and Signal Processing Magazine, 4–22
Maniezzo, V. (1994) Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions on Neural Networks, 5(1):39–53
Mayley, G. (1997) Landscapes, learning costs, and genetic assimilation. Evolutionary Computation, 4(3):213–234
McDonnell, J. R., Waagen, D. (1994) Evolving recurrent perceptions for time-series modelling. IEEE Transactions on Neural Networks, 5(1):24–38
Menczer, F., Parisi, D. (1992) Evidence of hyperplanes in the genetic learning of neural networks. Biological Cybernetics, 66:283–289
Merelo, J. J., Paton, M., Canas, A., Prieto, A., Moran, F. (1993) Optimization of a competitive learning neural network by genetic algorithms. In Proceedings of the International Workshop on Artificial Neural Networks, 185–192
Michalewicz, Z. (1996) Genetic Algorithms + Data Structures — Evolution Programs. Berlin: Springer-Verlag
Miller, G. F., Todd, P. M., Hegde, S. U. (1989) Designing neural networks using genetic algorithms. In J. D. Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, 379–384. San Meteo, CA: Morgan Kaufmann
Mitchell, M. (1996) An Introduction to Genetic Algorithms. Cambridge, MA: MIT Press
Montana, D. J., Davis, L. (1989) Training feedforward neural network using genetic algorithms. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, 762–767
Mozer, M. C. (1992) Induction of multiscale temporal structure. In J. E. Moody, S. J. Hanson, and R. P. Lippmann, editors, Advances in Neural Information Processing Systems 4, 275–282. San Mateo, CA: Morgan Kaufmann
Nolfi, S., Elman, J. L., Parisi, D. (1994) Learning and evolution in neural networks. Adaptive Behavior, 3:5–28
Omatu, S., Yoshioka, M. (1997) Self-tuning neuro-PID control and applications. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 1985–1989
Omlin, C. W., Giles, C. L. (1996) Rule revision with recurrent neural networks. IEEE Transactions on Knowledge and Data Engineering, 8(1): 183–188
Paredis, J. (1996) Coevolutionary life-time learning. In H.-M. Voigt, W. Ebeling, I. Rechenberg, and H.-P. Schwefel, editors, Parallel Problem Solving from Nature — PPSN IV, 72–80. Berlin: Springer-Verlag
Parisi, D., Nolfi, S. (1996) The influence of learning on evolution. In R. K. Belew and M. Mitchell, editors, Adaptive Individuals in Evolving Populations: Models and Algorithms, 419–428. Reading, MA: Addison-Wesley
Pineda, F. J. (1987) Generalization of backpropagation to recurrent neural networks. Physical Review Letters, 59:2229–2232
Port, R. F. (1990) Representation and recognition of temporal patterns. Connection Science, 2:151–176
Porto, V. W., Fogel, D. B., Fogel, L. J. (1995) Alternative neural networks training methods. IEEE Expert, 10(3):16–22
Rechenberg, I. (1989) Evolution strategy: Nature’s way of optimization. In Optimization: Methods and Applications, Possibilities and Limitations, volume 47 of Lecture Notes in Engineering. Berlin: Springer-Verlag
Riedmiller, M., Braun, H. (1993) A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In Proceedings of the International Conference on Neural Networks, 586–591
Rudolph, G. (1991) Global optimization by means of distributed evolution strategies. In H. P. Schwefel and R. Männer, editors, Parallel Problem Solving from Nature — PPSN I, 209–213. Berlin: Springer-Verlag
Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1986) Learning internal representations by error propagation. In D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, editors, Parallel Distribution Processing: Explorations in the Micro structure of Cognition. Vol. 1: Foundation. Cambridge, MA: MIT Press
Saravanan, N., Fogel, D. B. (1995) Evolving neural control systems. IEEE Expert, 10(3):23–27
Sasaki, T., Tokoro, M. (1998) Adaptation under changing environments with various rates of inheritance of acquired characters: Comparison between Darwinian and Lamarckian evolution. In Proceedings of the Second Asia-Pacific Conference on Simulated Evolution and Learning, 34–41
Schwefel, H.-P. (1995) Evolution and Optimum Seeking. New York: Wiley
Sejnowski, T. J., Rosenberg, C. R. (1987) Parallel networks that learn to pronounce English text. Complex Systems, 1:145–168
Skinner, A. J., Broughton, J. Q. (1995) Neural networks in computational materials science: Training algorithms. Modelling and Simulation in Materials Science and Engineering, 3:371–389
Solis, F. J., Wets, R. J-B. (1981) Minimization by random search techniques. Mathematics of Operations Research, 6(1):19–30
Turney, P. (1996) Myths and legends of the Baldwin effect. In Proceedings of the Workshop on Evolutionary Computing and Machine Learning at the 13th International Conference on Machine Learning, 135–142
Waibel, A. (1989) Modular construction of time-delay neural networks for speech recognition. Neural Computation, 1:39–46
Whitley, D. (1994) A genetic algorithm tutorial. Statistics& Computing, 4(2):65–85
Whitley, D., Gordon, V. S., Mathias, K. (1994) Lamarckian evolution, the Baldwin effect and function optimization. In Y. Davidor, H.-P. Schwefel, and R. Manner, editors, Parallel Problem Solving from Nature — PPSN HI, 6–15. Berlin: Springer-Verlag
Whitley, D., Starkweather, T., Bogart, C. (1990) Genetic algorithms and neural networks: Optimizing connections and connectivity. Parallel Computing, 14:347–361
Wieland, A. (1991) Evolving neural network controllers for unstable systems. In Proceedings of the International Joint Conference on Neural Networks, 667–673
Williams, R. J., Zipser, D. (1989) Experimental analysis of the real-time recurrent learning algorithm. Connection Science, 1:87–111
Williams, R. J., Zipser, D. (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1:270–280
Wu, K. H., Chen, C. H., Lee, J. D. (1996) Cache-genetic-based modular fuzzy neural networks for robot path planning. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 3089–3094
Yao, X. (1999) Evolving artificial neural networks. Proceedings of the IEEE, 87(9):1423–1447
Yao, X., Liu, Y. (1997) A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks, 8(3):694–713
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ku, K.W.C., Mak, M.W., Siu, W.C. (2003). Approaches to Combining Local and Evolutionary Search for Training Neural Networks: A Review and Some New Results. In: Ghosh, A., Tsutsui, S. (eds) Advances in Evolutionary Computing. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18965-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-18965-4_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-62386-8
Online ISBN: 978-3-642-18965-4
eBook Packages: Springer Book Archive