Abstract
To analyze adaptation capabilities of individuals and agents in constantly changing environments, we suggested using of connectionist methodology and the solution of sequences of different pattern recognition tasks. Each time after the task change, we start training from previous perceptron weight vector. We found that large values of components of the weight vector decrease the gradient and learning speed. A noise injected into the desired outputs of the perceptron is used as a “natural” method to control the weight growth and adaptation to new environment. To help artificial population to withstand lengthy sequences of strong catastrophes, populations with offspring and ”genetic” inheritance of the noise intensity parameter have to be created. It was found that the optimal interval for the noise intensity follows power of environmental changes. To improve the survivability of synthetic populations, we suggest “mother’s training”, and partial protection of offspring from artificially corrupted training signals. New simulation methodology could help explain known technical, biological, psychological and social phenomena and behaviors in quantitative way.
This is a preview of subscription content, log in via an institution to check access.
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
Anderson, J.R., Lebiere, C.: The Atomic Components of Thought. Lawrence Erlbaum Associates, Mahwah (1998)
Cortez, P., Rocha, M., Neves, J.: A Lamarckian approach for neural network training. Neural Processing Letters 15, 105–116 (2002)
French, V.A., Anderson, E., Putman, G., Alvager, T.: The Yerkes-Dodson law simulated with an artificial neural network. Complex Systems 5(2), 136–147 (1999)
Haykin, S.: Neural Networks: A comprehensive foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1999)
Hinton, G.E., Nowlan, S.J.: How learning guides evolution. Complex Systems 1, 497–502 (1987)
Ku, K.W.C., Mak, M.W., Sin, W.C.: A study of the Lamarckian evolution of recurrent neural networks. IEEE Trans. on Evolutionary Computation 4(1), 31–42 (2000)
Newell, A., Simon, H.A.: Computer science as empirical enquiry: symbols and search. Communications of the Association for Computing Machinery 19, 113–126 (1976)
Nolfi, S., Floreano, D.: Learning and evolution. Autonomous Robots 7, 89–113 (1999)
Miglino, O., Lund, H.H., Nolfi, S.: Evolving mobile robots in simulated and real environments. Artificial Life 2, 417–434 (1995)
Raudys, S.: Evolution and generalization of a single neurone. I. SLP as seven statistical classifiers. Neural Networks 11(2), 283–296 (1998)
Raudys, S.: Statistical and Neural Classifiers: An integrated approach to design. Springer, Heidelberg (2001)
Raudys, S.: An adaptation model for simulation of aging process. Int. J. Modern Physics C 13(8), 1075–1086 (2002)
Raudys, S., Amari, S.: Effect of initial values in simple perception. In: Proc. IEEE World Congress on Computational Intelligence, IJCNN 1998, pp. 1530–1535. IEEE Press, Los Alamitos (1998)
Raudys, S., Justickis, V.: Yerkes-Dodson law in agents’ training. In: Pires, F.M., Abreu, S.P. (eds.) EPIA 2003. LNCS (LNAI), vol. 2902, pp. 54–58. Springer, Heidelberg (2003)
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, vol. I, pp. 318–362. Bradford Books, Cambridge (1986)
Weng, J., McClelland, J., Pentland, A., Sporns, O., Stockman, I., Sur, M., Thelen, E.: Autonomous mental development by robots and animals. Science 291(5504), 599–600 (2001)
Yao, X.: Evolving artificial neural networks. Proceedings IEEE 87, 1423–1447 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Raudys, Š. (2004). Survival of Intelligent Agents in Changing Environments. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds) Artificial Intelligence and Soft Computing - ICAISC 2004. ICAISC 2004. Lecture Notes in Computer Science(), vol 3070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24844-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-24844-6_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22123-4
Online ISBN: 978-3-540-24844-6
eBook Packages: Springer Book Archive