Learning to Adapt to Changing Environments in Evolving Neural Networks

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.

[1]  J. Baldwin.  A New Factor in Evolution , 1896, The American Naturalist.

[2]  C. Waddington.  Canalization of Development and the Inheritance of Acquired Characters , 1942, Nature.

[3]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[4]  P. Richerson,et al.  Culture and the Evolutionary Process , 1988 .

[5]  C. Lumsden.  Culture and the Evolutionary Process, Robert Boyd, Peter J. Richerson. University of Chicago Press, Chicago & London (1985), viii, +301. Price $29.95 , 1986 .

[6]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[7]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[8]  John Maynard Smith,et al.  When learning guides evolution , 1987, Nature.

[9]  Geoffrey E. Hinton,et al.  How Learning Can Guide Evolution , 1996, Complex Syst..

[10]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[11]  John F. Kolen,et al.  Backpropagation is Sensitive to Initial Conditions , 1990, Complex Syst..

[12]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .

[13]  Stefano Nolfi,et al.  Econets: Neural networks that learn in an environment , 1990 .

[14]  V. Marchman,et al.  U-shaped learning and frequency effects in a multi-layered perception: Implications for child language acquisition , 1991, Cognition.

[15]  David H. Ackley,et al.  Interactions between learning and evolution , 1991 .

[16]  P. Todd,et al.  Exploring Adaptive Agency I: Theory and Methods for Simulating the Evolution of Learning , 1991 .

[17]  Peter M. Todd,et al.  Exploring adaptive agency II: simulating the evolution of associative learning , 1991 .

[18]  Stefano Nolfi,et al.  Auto-teaching: networks that develop their own teaching input , 1993 .

[19]  L. Darrell Whitley,et al.  Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect , 1993, Evolutionary Computation.

[20]  Francesco Mondada,et al.  Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[21]  D. Parisi,et al.  Phenotypic plasticity in evolving neural networks , 1994, Proceedings of PerAc '94. From Perception to Action.

[22]  Jeffrey L. Elman,et al.  Learning and Evolution in Neural Networks , 1994, Adapt. Behav..