Learning to Adapt to Changing Environments in Evolving Neural Networks

Abstract

To study learning as an adaptive process, one must take into consideration the role of evolution, which is the primary adaptive process. In addition, learning should be studied in (artificial) organisms that live in an independent physical environment in such a way that the input from the environment can be at least partially controlled by the organisms' behavior. To explore these issues, we used a genetic algorithm to simulate the evolution of a population of neural networks, each controlling the behavior of a small mobile robot that must explore efficiently an environment surrounded by walls. Because the environment changes from one generation to the next, each network must learn during its life to adapt to the particular environment into which it happens to be born. We found that evolved networks incorporate a genetically inherited predisposition to learn that can be described as (1) the presence of initial conditions that tend to canalize learning in the right directions; (2) the tendency to behave in a way that enhances the perceived differences between different environments and determines input stimuli that facilitate the learning of adaptive changes; and (3) the ability to reach desirable stable states.

Keywords

learning evolution environmental changes adaptation

Get full access to this article

View all access options for this article.

References

Ackley, D.E. , & Littman, M.L. (1991). Interaction between learning and evolution. In C. G. Langton et al. (Eds.), Proceedings of the Second Conference on Artificial Life. Reading, MA: Addison-Wesley.

Baldwin, J.M. (1896). A new factor in evolution. American Naturalist, 30, 441-451.

Belew, R.K. , McInerney, J. , & Schraudolph, N.N. (1991). Evolving networks: Using the genetic algorithm with connectionistic learning. In C.G. Langton et al. (Eds.), Proceedings of the Second Conference on Artificial Life. Reading, MA : Addison-Wesley.

Boyd, R. , & Richerson, P.J. (1985). Culture and the evolutionary process. Chicago: University of Chicago Press.

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.

Hinton, G.E. , & Nowlan, S.J. (1987). How learning guides evolution. Complex Systems, 1, 495-502.

Holland, J.J. (1975). Adaptation in natural and artificial systems. Ann Arbor: University of Michigan Press.

Kitano, H. (1990). Designing neural networks using genetic algorithms with graph generation system. Complex Systems, 4, 461-476.

Kolen, J.F. , & Pollack, J.B. (1990). Back-propagation is sensitive to the initial conditions . Complex Systems, 4, 269-280.

10.

Miller, G.F. , & Todd, P.M. (1990). Exploring adaptive agency: I. Theory and methods for simulating the evolution of learning. In D. S. Touretzky, J. L. Elman, T. J. Sejnowski , and G. E. Hinton (Eds.), Proceedings of the 1990 Connectionist Models Stimmer School. San Mateo, CA: Morgan Kaufmann.

11.

Mondada, F. , Franzi, E. , & Ienne, P. (1993). Mobile robot miniaturisation: A tool for investigation in control algorithms . Proceedings of the Third International Symposium on Experimental Robotics. Kyoto, Japan.

12.

Nolfi, S. , Elman, J.L. , & Parisi, D. (1994a). Learning and evolution in neural networks. Adaptive Behavior; 3, 5-28.

13.

Nolfi, S. , Miglino, O. , & Parisi, D. (1994b). Phenotypic plasticity in evolving neural networks . In D. P Gaussier & J-D. Nicoud (Eds.), Proceedings of the International Conference from Perception to Action. Los Alamitos, CA : IEEE Press.

14.

Nolfi, S. , & Parisi, D. (1993). Auto-teaching: Networks that develop their own teaching input. In J. L. Deneubourg, H. Bersini, S. Goss, G. Nicolis, & R. Dagonnier (Eds.), Proceedings of the Second European Conference on Artificial Life. Brussels: Free University of Brussels.

15.

Nolfi, S. , & Parisi, D. (1994). Desired responses do not correspond to good teaching input in ecological neural networks. Neural Processing Letters , 2, 1-4.

16.

Parisi, D. , Cecconi, F. , & Nolfi, S. (1990). Econets: Neural networks that learn in an environment . Network, 1, 149-168.

17.

Parisi, D. , & Nolfi, S. (1995). How learning can influence evolution within a non-Lamarckian framework. In R. K. Belew & M. Mitchell (Eds.), Plastic individuals in evolving populations. Reading, MA: SFI Series, Addison-Wesley.

18.

Plunkett, K. , & Marchman, V. (1991). U-shaped learning and frequency effects in a multi-layered perceptron: Implications for child language acquisition. Cognition, 38,43-102.

19.

Rumelhart, D.E. , Hinton, G.E. , & Williams, R.J. (1986). Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing: 1: Foundations. Cambridge, MA: MIT Press.

20.

Rumelhart, D.E. , & McClelland, J.L. (1986). Parallel distributed processing . Cambridge, MA: MIT Press.

21.

Todd, P.M. , & Miller, G.F. (1991). Exploring adaptive agency: II. Simulating the evolution of associative learning. In J.-A. Meyer and S. W Wilson (Eds.), From animals to animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press.

22.

Waddington, C.H. (1942). Canalization of development and the inheritance of acquired characters. Nature, 150, 563-565.