A Note on Learning and Evolution in Neural Networks

Interactions between evolution and lifetime learning are of great interest to studies of adaptive behaviour both in the natural world and the field of evolutionary computation. This contribution revisits an earlier discovered observation that the average performance of a population of neural networks which are evolved to solve one task is improved by lifetime learning on a different task. Two existing, and very different, explanations of this phenomenon are summarised and examined. Experimental results are presented that demonstrate that neither of these explanations are sufficient to fully explain the phenomenon. A new explanation, together with experimental justification, is presented which describes the effect in terms of lifetime learning providing a buffer against the potentially deleterious effects of mutation.

• Type: Conference
• Year: 2000
• Where: GECCO
• Authors: Brian Carse, Johan Oreland
• Keywords: Adaptive Behaviour, Earlier Discovered Observation, GECCO 2000, Lifetime Learning, Optimization