On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks
Open Access
- 13 November 2013
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 8 (11) , e79138
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.Keywords
This publication has 61 references indexed in Scilit:
- The evolutionary origins of modularityProceedings Of The Royal Society B-Biological Sciences, 2013
- Comparing biological networks via graph compressionBMC Systems Biology, 2010
- Modular and Hierarchically Modular Organization of Brain NetworksFrontiers in Neuroscience, 2010
- A Hypercube-Based Encoding for Evolving Large-Scale Neural NetworksArtificial Life, 2009
- Where neuroscience and dynamic system theory meet autonomous robotics: A contracting basal ganglia model for action selectionNeural Networks, 2008
- From Swimming to Walking with a Salamander Robot Driven by a Spinal Cord ModelScience, 2007
- Evolution on a Restless Planet: Were Environmental Variability and Environmental Change Major Drivers of Human Evolution?2005
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Evolution of Reinforcement Learning in Uncertain Environments: A Simple Explanation for Complex Foraging BehaviorsAdaptive Behavior, 2002
- PerceptronsThe American Journal of Psychology, 1971