Abstract of: “On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks”

A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural net-works are (1) the developmental process that links genes to nervous systems, which enables the evolution of large, regu-lar neural networks, and (2) synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. One of the main challenge when designing Artificial Neu-ral Networks (ANN) with learning abilities is to make them capable of learning in a large class of situations. When arti-ficial evolution is used to design a plastic ANN, the topology of the networks is the result of the interactions between th