Myths and Legends of the Baldwin Effect

This position paper argues that the Baldwin effect is widely misunderstood by the evolutionary computation community. The misunderstandings appear to fall into two general categories. Firstly, it is commonly believed that the Baldwin effect is concerned with the synergy that results when there is an evolving population of learning individuals. This is only half of the story. The full story is more complicated and more interesting. The Baldwin effect is concerned with the costs and benefits of lifetime learning by individuals in an evolving population. Several researchers have focussed exclusively on the benefits, but there is much to be gained from attention to the costs. This paper explains the two sides of the story and enumerates ten of the costs and benefits of lifetime learning by individuals in an evolving population. Secondly, there is a cluster of misunderstandings about the relationship between the Baldwin effect and Lamarckian inheritance of acquired characteristics. The Baldwin effect is not Lamarckian. A Lamarckian algorithm is not better for most evolutionary computing problems than a Baldwinian algorithm. Finally, Lamarckian inheritance is not a better model of memetic (cultural) evolution than the Baldwin effect.

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

[2]  H. Osborn.  OYTOGENIC AND PHYLOGENIC VARIATION. , 1896, Science.

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

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

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

[6]  G. Simpson.  THE BALDWIN EFFECT , 1953 .

[7]  Paul E. Utgoff,et al.  Shift of bias for inductive concept learning , 1984 .

[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]  David Haussler,et al.  Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework , 1988, Artif. Intell..

[11]  W. Wcislo.  BEHAVIORAL ENVIRONMENTS AND EVOLUTIONARY CHANGE , 1989 .

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

[13]  Pablo Moscato,et al.  On Evolution, Search, Optimization, Genetic Algorithms and Martial Arts : Towards Memetic Algorithms , 1989 .

[14]  M. West-Eberhard.  Phenotypic Plasticity and the Origins of Diversity , 1989 .

[15]  J. Fontanari,et al.  Stochastic versus deterministic update in simulated annealing , 1990 .

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

[17]  P. Moscato.  A Competitive-cooperative Approach to Complex Combinatorial Search , 1991 .

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

[19]  S. Gould.  Bully for brontosaurus : reflections in natural history , 1991 .

[20]  L. Cosmides,et al.  The Adapted mind : evolutionary psychology and the generation of culture , 1992 .

[21]  MoscatoPablo.  An introduction to population approaches for optimization and hierarchical objective functions , 1993 .

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

[23]  Inman Harvey.  The Puzzle of the Persistent Question Marks : A Case Study of Genetic Drift , 1993, ICGA.

[24]  S. Scheiner.  Genetics and Evolution of Phenotypic Plasticity , 1993 .

[25]  W. Hart.  Adaptive global optimization with local search , 1994 .

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

[27]  E. Sober.  The adaptive advantage of learning and a priori prejudice , 1994 .

[28]  S. Pinker,et al.  The Language Instinct: How the Mind Creates Language , 1994 .

[29]  William E. Hart,et al.  The Role of Development in Genetic Algorithms , 1994, FOGA.

[30]  Filippo Menczer,et al.  EVOLVING SENSORS IN ENVIRONMENTS OF CONTROLLED COMPLEXITY , 1994 .

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

[32]  Patrick D. Surry,et al.  Formal Memetic Algorithms , 1994, Evolutionary Computing, AISB Workshop.

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

[34]  Gary Cziko,et al.  Without Miracles: Universal Selection Theory and the Second Darwinian Revolution , 1995 .

[35]  Russell W. Anderson.  Genetic Mechanisms Underlying the Baldwin Effect Are Evident in Natural Antibodies , 1995, Evolutionary Programming.

[36]  V. Nanjundiah,et al.  An investigation into the role of phenotypic plasticity in evolution. , 1995, Journal of theoretical biology.

[37]  Edmund K. Burke,et al.  A Memetic Algorithm for University Exam Timetabling , 1995, PATAT.

[38]  Filippo Menczer,et al.  Maturation and the Evolution of Imitative Learning in Artificial Organisms , 1995, Adapt. Behav..

[39]  S. Pinker.  The language instinct : how the mind creates language , 1995 .

[40]  R. Anderson,et al.  Learning and evolution: a quantitative genetics approach. , 1995, Journal of theoretical biology.

[41]  Peter D. Turney.  Cost-Sensitive Classification: Empirical Evaluation of a Hybrid Genetic Decision Tree Induction Algorithm , 1994, J. Artif. Intell. Res..

[42]  Vasant Honavar,et al.  Evolutionary Design of Neural Architectures -- A Preliminary Taxonomy and Guide to Literature , 1995 .

[43]  Ben Paechter,et al.  Extensions to a Memetic Timetabling System , 1995, PATAT.

[44]  Alan S. Perelson,et al.  The Baldwin effect in the immune system: learning by somatic hypermutation , 1996 .

[45]  William E. Hart,et al.  Optimization with genetic algorithm hybrids that use local searches , 1996 .