GECCO Best Paper Award  

Dr. John Bullinaria (Cercia Deputy Director) received a Best Paper Award at the Genetic and Evolutionary Computation Conference (GECCO-2007) held in London 7-11 July 2007. This is the main annual international conference in the field of evolutionary computation. His paper entitled "The Effect of Learning on Life History Evolution" investigated how periods of parental protection can affect learning and result in better adult performance. Such ideas can be applied to artificial systems to evolve better adaptable systems for real world applications.

Published Abstract: A series of evolutionary neural network simulations are presented which explore the hypothesis that learning factors can result in the evolution of long periods of parental protection and late onset of maturity. By evolving populations of neural networks to learn quickly to perform well on simple classification tasks, it is shown that better learned performance is obtained if protection from competition is provided during the network’s early learning period. Moreover, if the length of the protection period is allowed to evolve, it does result in the emergence of relatively long protection periods, even if there are other costs involved, such as individuals not being allowed to reproduce during their protection phase, and the parents suffering increased risk of dying while protecting their offspring.

Link to full paper: http://www.cs.bham.ac.uk/~jxb/PUBS/LELHE.pdf