Nothing Special   »   [go: up one dir, main page]

On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks

PLoS One. 2013 Nov 13;8(11):e79138. doi: 10.1371/journal.pone.0079138. eCollection 2013.

Abstract

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 networks are (1) the developmental process that links genes to nervous systems, which enables the evolution of large, regular 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. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT). Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1) in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2) whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Computer Simulation*
  • Models, Neurological
  • Neural Networks, Computer*

Grants and funding

This work was funded by the Agence Nationale de la Recherche (http://www.agence-nationale-recherche.fr/) by the grants Creadapt (ANR-12-JS03-0009) and EvoNeuro (ANR-09-EMER-005). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.