Stability and task complexity: a neural network model of evolution and learning

Authors:
James R. Watson;Nicholas Geard;Janet Wiles
Affiliations:
School of Information Technology and Electrical Engineering, The University of Queensland, Australia;School of Information Technology and Electrical Engineering, The University of Queensland, Australia;School of Information Technology and Electrical Engineering and School of Psychology, The University of Queensland, Australia
Venue:
ICAL 2003 Proceedings of the eighth international conference on Artificial life
Year:
2002

Citing 3
Cited 1

An introduction to genetic algorithms

An introduction to genetic algorithms
On the Baldwin effect

Artificial Life
The Puzzle of the Persistent Question Marks: A Case Study of Genetic Drift

Proceedings of the 5th International Conference on Genetic Algorithms

Transient Phenomena in Learning and Evolution: Genetic Assimilation and Genetic Redistribution

Artificial Life

Quantified Score

Hi-index	0.00

Visualization

Abstract

Since Hinton and Nowlan introduced the Baldwin effect to the evolutionary computation community, agent-based studies of genetic assimilation have uncovered many details of the dynamic processes involved. In a previous paper, we demonstrated genetic assimilation with a simple food/toxin discrimination task using neural network agents that could evolve their learning rate. The study reported in this paper investigated the genetic assimilation of more complex learning tasks.Kauffman's NK landscape model, which can generate landscapes with a variable degree of correlation, was used to define learning tasks of varying levels of complexity. Simulations indicate an increased tendency of genetic assimilation to occur as the complexity of the learning task decreases and the environmental stability increases. These results are explained in terms of the shifting balance between the evolutionary costs and benefits of learning.