Abstract
Currently, the standard in supervised Artificial Neural Networks (ANNs) research is to use the backpropagation (BP) algorithm or one of its improved variants, for training. In this chapter, we present an improvement to the most widely used BP learning algorithm using (1+1) evolutionary Strategy (ES), one of the most widely used artificial evolution paradigms. The goal is to provide a method that can adaptively change the main learning parameters of the BP algorithm in an unconstrained manner. The BP/ES algorithm we propose is simple to implement and can be used in combination with various improved versions of BP. In our experimental tests we can see a substantial improvement in ANN performance, in some cases a reduction of more than 50% in error for time series prediction on a standard benchmark test. Therefore, we believe that our proposal effectively combines the learning abilities of BP with the global search of ES to provide a useful tool that improves the quality of learning for BP-based methods.
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
Belew, R.K., McInerney, J., Schraudolph, N.N.: Evolving networks:Using the Genetic Algorithm with connectionist learning. In: Proc. Second Artificial Life Conference, NewYork, pp. 511–547. Addison-Wesley, Reading (1991)
De Jong, K.: A unified approach to Evolutionary Computation. In: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers, GECCO 2009, Montreal, Québec, Canada, July 08-12, pp. 2811–2824. ACM, New York (2009)
Eiben, A.E., Smith, J.E.: 2003 Introduction to Evolutionary Computing. Springer, Heidelberg (2003)
Frean, M.: The upstart algorithm: A method for constructing and training feedforward neural networks. Neural Computation 2(2), 198–209 (1990)
Gurney, K.: An Introduction to Neural Networks. Taylor & Francis, Inc., Abington (1997)
Hagan, M.T., Demuth, H.B., Beale, M.: Neural Network Design. PWS Publishing Co. (1996)
Harp, S.A., Samad, T., Guha, A.: Toward the genetic synthesis of neural networks. In: Schaffer, J.D. (ed.) Proc. 3rd Int. Conf. Genetic Algorithms and Their Applications, pp. 360–369. Morgan Kaufmann, San Mateo (1989)
Pedro, I.V.: Redes Neuronales Artificiales: Un Enfoque Práctico. Pearson Educacion, London (2004)
Jacobs, R.A.: Increased Rates of Convergence Through Learning Rate Adaptation. Technical Report. UMI Order Number: UM-CS-1987-117., University of Massachusetts (1987)
Kim, H.B., Jung, S.H., Kim, T.G., Park, K.H.: Fast learning method for back-propagation neural network by evolutionary adaptation of learning rates. Neurocomput. 11(1), 101–106 (1996)
Lee, S.-W.: Off-line recognition of totally unconstrained handwritten numerals using multilayer cluster neural network. IEEE Trans. Pattern Anal. Machine Intell. 18, 648–652 (1996)
Merelo, J.J., Paton, M., Cañas, A., Prieto, A., Moran, F.: Optimization of a competitive learning neural network by genetic algorithms. In: Mira, J., Cabestany, J., Prieto, A.G. (eds.) IWANN 1993. LNCS, vol. 686, pp. 185–192. Springer, Heidelberg (1993)
Patel, D.: Using genetic algorithms to construct a network for financial prediction. In: Proc. SPIE: Applications of Artificial Neural Networks in Image Processing, Bellingham, WA, pp. 204–213 (1996)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Foundations. MIT Press Computational Models of Cognition And Perception Series, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)
Samarasinghe, S.: Neural Networks for Applied Sciences and Engineering. Auerbach Publications (2006)
Schefel, H.-P.: Numerische Optimierung von Computer-Modellen mittels der Wvolutionsstrategie. ISR, vol. 26. Birkhaeuser, Basel (1997)
Skinner, A.J., Broughton, J.Q.: Neural networks in computational materials science: Training algorithms. Modeling and Simulation in Materials Sci. Eng. 3(3), 371–390 (1995)
Topchy, A.P., Lebedko, O.A.: Neural network training by means of cooperative evolutionary search. Nuclear Instrum. Methods in Phys. Res., Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 389(1-2), 240–241 (1997)
Whitehead, B.A., Choate, T.D.: Evolving space-filling curves to distribute radial basis functions over an input space. IEEE Trans. Neural Networks 5, 15–23 (1994)
Whitley, D., Starkweather, T., Bogart, C.: Genetic algorithms and neural networks: Optimizing connections and connectivity. Parallel Comput 14(3), 347–361 (1990)
Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)
Liu, Y., Yao, X.: Evolutionary design of artificial neural networks with different nodes. In: Proc. 1996 IEEE Int. Conf. Evolutionary Computation (ICEC 1996), Nagoya, Japan, pp. 670–675 (1996)
Hwang, M.W., Choi, J.Y., Park, J.: Evolutionary projection neural networks. In: Proc. 1997 IEEE Int. Conf. Evolutionary Computation, ICEC 1997, pp. 667–671 (1997)
Sebald, A.V., Chellapilla, K.: On making problems evolutionarily friendly, part I: Evolving the most convenient representations. In: Porto, W., Saravanan, N., Waagen, D., Eiben, A.E. (eds.) EP 1998. LNCS, vol. 1447, pp. 271–280. Springer, Heidelberg (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Galaviz, J.P., Melin, P., Trujillo, L. (2010). Improvement of the Backpropagation Algorithm Using (1+1) Evolutionary Strategies. In: Melin, P., Kacprzyk, J., Pedrycz, W. (eds) Soft Computing for Recognition Based on Biometrics. Studies in Computational Intelligence, vol 312. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15111-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-15111-8_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15110-1
Online ISBN: 978-3-642-15111-8
eBook Packages: EngineeringEngineering (R0)