The rise and fall of learning: a neural network model of the genetic assimilation of acquired traits

Watson, James and Wiles, Janet (2002). The rise and fall of learning: a neural network model of the genetic assimilation of acquired traits. In: D. Fogel, M. El-Sharkawi and et al., Proceedings of the 2002 Congress on Evolutionary Computation. The 2002 Congress on Evolutionary Computation (CEC 2002), Hawaii, United States, (600-605). 12-17 May 2002.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
cec-2002.pdf cec-2002.pdf application/pdf 230.12KB 273
Author Watson, James
Wiles, Janet
Title of paper The rise and fall of learning: a neural network model of the genetic assimilation of acquired traits
Conference name The 2002 Congress on Evolutionary Computation (CEC 2002)
Conference location Hawaii, United States
Conference dates 12-17 May 2002
Proceedings title Proceedings of the 2002 Congress on Evolutionary Computation
Journal name Cec'02: Proceedings of the 2002 Congress On Evolutionary Computation, Vols 1 and 2
Place of Publication New York City, United States
Publisher IEEE
Publication Year 2002
Sub-type Fully published paper
Open Access Status File (Author Post-print)
ISBN 0780372824
Editor D. Fogel
M. El-Sharkawi
et al.
Start page 600
End page 605
Total pages 6
Language eng
Abstract/Summary The genetic assimilation of learned behaviour was introduced to the wider evolutionary computation field by the classic simulation of Hinton and Nowlan. Subsequent studies have analysed and extended their initial framework, contributing to the understanding of the often counterintuitive relationship between evolution and learning. We add to this increasing body of literature by presenting an evolving population of neural networks that plainly exhibit the Baldwin effect. Phenotypic plasticity, embodied in the literal learning rate of the neural networks, is evolved along with the network connection weights. Significantly, high levels of plasticity do not cause the population to genetically stagnate once correct behaviour can be learned. Rather, continuing inter-population competition drives the levels of learning down as beneficial behaviour becomes genetically specified. By observing the evolving learning rate of the agent population, and by comparing learned and innate agent responses, we demonstrate the Baldwin effect in its entirety.
Keyword Genetic assimilation
Evolution
Learning
Baldwin effect
References [1] Anderson, R. W. (1995). Learning and evolution: A quantitative genetics approach. Journal of Theoretical Biology, 175:89-101. [2] Baldwin, J. M. (1896). A new factor in evolution. American Naturalist, 30:441-451 536-553. Reproduced in Belew, R. K. & Mitchell, M. (Eds.), Adaptive Individuals in Evolving Populations. Addison-Wesley, Reading, MA. [3] Belew, R. K. (1990). Evolution, learning and culture: computational metaphors for adaptive search. Complex Systems, 4(1):11-49. [4] Chalmers, D. (1990). The evolution of learning: An experiment in genetic connectionism. Proceedings of the 1990 Connectionist Summer School, pages 81-90. [5] Darwin, C. (1859). The Origin of Species by Means of Natural Selection. The Modern Library. [6] Fontanari, J. F. and Meir, R. (1990). The effect of learning on the evolution of asexual populations. Complex Systems, 4:401-414. [7] French, R. and Messinger, A. (1994). Genes, phenes and the Baldwin effect: Learning and evolution in a simulated population. In Brooks, R. A. and Maes, P., editors, Artificial Life IV, pages 277-282. [8] Gruau, F. and Whitley, L. D. (1993). Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect. Evolutionary Computation, 1(3):213-233. [9] Harvey, I. (1993). The puzzle of the persistent question marks: A case study of genetic drift. In Forrest, S., editor, Proceedings of the Fifth International Conference on Genetic Algorithms, pages 15-22, San Mateo, CA. Morgan Kaufmann. [10] Hinton, G. and Nowlan, S. (1987). How learning can guide evolution. Complex Systems, 1:495-502. [11] Jones, M. and Konstam, A. (1999). The use of genetic algorithms and neural networks to investigate the Baldwin effect. In Carroll, J., Hiddad, H., Oppenheim, D., Bryant, B., and Lamont, G. B., editors, Proceedings of the 1999 ACM Symposium on Applied Computing, pages 275-279. [12] Ku, K. W. C. and Mak, M. W. (1998). Empirical analysis of the factors that affect the Baldwin effect. In Eiben, A. E., Back, T., Schoenauer, M., and Schwefel, H.-P., editors, Parallel Problem Solving from Nature -PPSN V, pages 481-490, Berlin. Springer. [13] Mayley, G. (1996a). The evolutionary cost of learning. In Maes, P., Mataric, M. J., Meyer, J.-A., Pollack, J., and Wilson, S. W., editors, From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive behavior, pages 458-467. MIT Press. [14] Mayley, G. (1996b). Landscapes, learning costs and genetic assimilation. In Turney, P., Whitley, D., and Anderson, R., editors, Evolution, Learning and Instinct: 100 Years of the Baldwin Effect, Cambridge, Ma. MIT Press. [15] Mayley, G. (1997). Guiding or hiding: Explorations into the effects of learning on the rate of evolution. In Husbands, P. and Harvey, I., editors, The Proceedings of the Fourth European Conference on Artificial Life. [16] Mitchell, M. (1996). An Introduction to Genetic Algorithms. MIT Press, Cambridge, MA. [17] Morgan, L. C. (1896). On modification and variation. Science, 4:733-740. [18] Osborn, H. F. (1896). Ontogenic and phylogenic variation. Science, 4:786-789. [19] Smith, J. M. (1987). When learning guides evolution. Nature, 329:761-762. [20] Todd, P. M. and Miller, G. F. (1991). Exploring adaptive agency II: Simulating the evolution of associative learning. In Meyer, J. and Wilson, S., editors, From animals to animats: Proceedings of the First International Conference on Simulation of Adaptive Behaviour, pages 306-315. MIT Press, Cambridge. [21] Waddington, C. H. (1942). Canalization of development and the inheritance of acquired characters. Nature, 150:563-565. [22] Whitley, D., Gordon, V. S., and Mathias, K. (1994). Lamarckian evolution, the Baldwin effect and function optimization. Lecture Notes in Computer Science, 866:6-15. [23] Wiles, J., Schulz, R., Bolland, S., Tonkes, B., and Hallinan, J. (2001). Selection procedures for module discovery: Exploring evolutionary algorithms for cognitive science. In Moore, J. D. and Stenning, K., editors, Proceedings of the 23rd Annual Conference of the Cognitive Science Society (CogSci 2001), pages 1124-1129. Lawrence Erlbaum Associates.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Unknown

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 10 times in Thomson Reuters Web of Science Article | Citations
Google Scholar Search Google Scholar
Created: Mon, 17 May 2004, 10:00:00 EST by James Watson on behalf of School of Mathematics & Physics