A comparison of speciation, extinction, and complexification in neuroevolution with and without selection pressure
Author: 
Derek JamesAuthors Info & Claims
Derek JamesAuthors Info & ClaimsPages 529 - 530
Abstract
In the study of biological evolution, neutral theories are invoked by some researchers to explain the dynamics of evolving populations regardless of selection pressure. The current study compares the dynamics of speciation, extinction, and complexification in two sets of populations of evolving artificial neural networks. One set of populations evolved under selection pressure, their survival dependent upon performance at a control task, while the other set of populations had survivors chosen randomly. Despite predictions to the contrary, the results showed significant differences in all three dynamics, suggesting that neutral models are incomplete explanations at best and that selection pressure constrains evolutionary search in very specific ways.
References
[1]
Anderson, C.W. 1989. Learning to control an inverted pendulum using neural networks. IEEE Control Systems Magazine, 9: 31--37.
[2]
Hubbell, S.P. 2001. The Unified Neutral Theory of Biodiversity and Biogeography. Princeton University Press, Princeton.
[3]
James, D. and Tucker, P. 2004. A comparative analysis of simplification and complexification in the evolution of neural network topologies, In Proceedings of the 2004 Conference on Genetic and Evolutionary Computation (GECCO-2004).
[4]
Kimura, M. 1968. Evolutionary rate at the molecular level. Nature, 217: 624--626.
[5]
Kimura, M. 1983. The Neutral Theory of Molecular Evolution. Cambridge University Press, Cambridge.
[6]
Langdon, W.B. and Poli, R. 1997. Fitness Causes Bloat, Second On-line World Conference on Soft Computing in Engineering Design and Manufacturing.
[7]
McGill, B.J., Maurer, B.A. and Weiser, M.D. 2006. Empirical evaluation of neutral theory. Ecology, 87(6): 1411--1423.
[8]
Michie, D. and Chambers, R.A. 1968. BOXES: An experiment in adaptive control. In: E. Dale and D. Michie (Editors), Machine Intelligence. Oliver and Boyd, Edinburgh, UK.
[9]
Mitchell, M. 1996. An introduction to genetic algorithms. MIT Press, Cambridge, Mass.
[10]
Schaffer, J. and Cannon, R. 1966. On the control of unstable mechanical systems, In Automatic and Remote Control III: Proceedings of the Third Congress of the International Federation of Automatic Control.
[11]
Sepkoski, J.J. 1984. A kinetic model of Phanerozoic taxonomic diversity. Paleobiology, 10: 246--267.
[12]
Stanley, K. 2004. Efficient Evolution of Neural Networks through Complexification. Doctoral Thesis, The University of Texas at Austin, Austin, TX.
[13]
Wootton, J.T. 2006. Field-parameterization and experimental test of the neutral theory of biodiversity. Nature, 433: 309--312.
[14]
Yao, X. 1999. Evolving Artificial Neural Networks. Proceedings of the IEEE, 87(9): 1423--1447.
Index Terms
- A comparison of speciation, extinction, and complexification in neuroevolution with and without selection pressure
Recommendations
Improving Distributed Neuroevolution Using Island Extinction and Repopulation
Applications of Evolutionary ComputationAbstractNeuroevolution commonly uses speciation strategies to better explore the search space of neural network architectures. One such speciation strategy is the use of islands, which are also popular in improving the performance of distributed ...
Advanced tutorial on coevolution
GECCO '07: Proceedings of the 9th annual conference companion on Genetic and evolutionary computationThe advanced tutorial on coevolution continues the topics covered in the introductory coevolution tutorial with a view towards research conducted in the last eight years. We will explore two themes which have recently been identified: interaction, which ...
Population Diversity as a Selection Factor: Improving Fitness by Increasing Diversity
GECCO '16 Companion: Proceedings of the 2016 on Genetic and Evolutionary Computation Conference CompanionEvolutionary algorithms search for problem solutions by selecting individuals for survival and reproduction with a bias towards higher fitness. Such biases may lead to premature convergence on sub-optimal solutions. A bias toward greater diversity can ...
Comments
Information & Contributors
Information
Published In
July 2008
1814 pages
Copyright © 2008 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 12 July 2008
Check for updates
Author Tags
Qualifiers
- Poster
Conference
Acceptance Rates
Overall Acceptance Rate 1,669 of 4,410 submissions, 38%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 136Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in