A Note on Learning and Evolution in Neural Networks

Interactions between evolution and lifetime learning are of great interest to studies of adaptive behaviour both in the natural world and the field of evolutionary computation. This contribution revisits an earlier discovered observation that the average performance of a population of neural networks which are evolved to solve one task is improved by lifetime learning on a different task. Two existing, and very different, explanations of this phenomenon are summarised and examined. Experimental results are presented that demonstrate that neither of these explanations are sufficient to fully explain the phenomenon. A new explanation, together with experimental justification, is presented which describes the effect in terms of lifetime learning providing a buffer against the potentially deleterious effects of mutation.

[1]  J. David Schaffer,et al.  Proceedings of the third international conference on Genetic algorithms , 1989 .

[2]  J. Baldwin.  A New Factor in Evolution (Continued) , 1896, The American Naturalist.

[3]  Giles Mayley.  The Evolutionary Cost of Learning , 1996 .

[4]  Inman Harvey,et al.  Is There Another New Factor in Evolution? , 1996, Evolutionary Computation.

[5]  Maja J. Matarić,et al.  The Evolutionary Cost of Learning , 1996 .

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

[7]  Charles E. Taylor,et al.  Artificial Life II , 1991 .

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

[9]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

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

[11]  C. L. Morgan,et al.  ON MODIFICATION AND VARIATION. , 1896, Science.

[12]  Giles Mayley,et al.  Landscapes, Learning Costs, and Genetic Assimilation , 1996, Evolutionary Computation.

[13]  Domenico Parisi,et al.  Evolving organisms that can reach for objects , 1991 .

[14]  Inman Harvey.  Relearning and Evolution in Neural Networks , 1995, Adapt. Behav..

[15]  Stefano Nolfi,et al.  The influence of learning on evolution , 1996 .

[16]  L. Darrell Whitley,et al.  Lamarckian Evolution, The Baldwin Effect and Function Optimization , 1994, PPSN.

[17]  T. Jukes,et al.  The neutral theory of molecular evolution. , 2000, Genetics.

[18]  Inman Harvey,et al.  Unicycling Helps Your French: Spontaneous Recovery of Associations by Learning Unrelated Tasks , 1996, Neural Computation.

[19]  Brian Carse,et al.  Tackling the "Curse of Dimensionality" of Radial Basis Functional Neural Networks Using a Genetic Algorithm , 1996, PPSN.

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

[21]  Richard K. Belew,et al.  When Both Individuals and Populations Search: Adding Simple Learning to the Genetic Algorithm , 1989, ICGA.

[22]  Frédéric Gruau,et al.  The cellular development of neural networks: the interaction of learning and evolution , 1993 .

[23]  R. French,et al.  Genes, Phenes and the Baldwin Effect: Learning and Evolution in a Simulated Population , 1994 .

[24]  Melanie Mitchell,et al.  To adaptive individuals in evolving populations , 1996 .

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

[26]  F. Varela,et al.  Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life , 1992 .