Genetic Algorithms for Tracking Changing Environments
Proceedings of the 5th International Conference on Genetic Algorithms
Training feedforward neural networks using genetic algorithms
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
The Influence of Learning in the Evolution of Busy Beavers
Proceedings of the EvoWorkshops on Applications of Evolutionary Computing
Hi-index | 0.00 |
In this paper, we study the relationship between learning and evolution in a simple abstract model, where neural networks capable of learning are evolved through genetic algorithms (GAs). The connective weights of individuals' neural networks undergo modification, i.e., certain characters will be acquired, through their lifetime learning. By setting various rates for the heritability of acquired characters, which is a motive force of Lamarckian evolution, we observe adaptational processes of the populations over successive generations. Paying particular attention to behaviours under changing environments, we show the following results. The population with the lower rate of heritability not only shows more stable behaviour against environmental changes, but also maintains greater adaptability with respect to such changing environments. Consequently, the population with zero heritability, i.e., the Darwinian population, attains the highest level of adaptation toward dynamic environments.