On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks

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.
Complete list of metadatas

Cited literature [67 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01264752
Contributor : Jean-Baptiste Mouret <>
Submitted on : Friday, January 29, 2016 - 4:17:21 PM
Last modification on : Thursday, July 11, 2019 - 2:10:07 PM
Long-term archiving on : Friday, November 11, 2016 - 8:42:08 PM

File

2013ACLI2965.pdf
Files produced by the author(s)

Identifiers

Citation

Paul Tonelli, Jean-Baptiste Mouret. On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks. PLoS ONE, Public Library of Science, 2013, 8 (11), pp.e79138. ⟨http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0079138⟩. ⟨10.1371/journal.pone.0079138⟩. ⟨hal-01264752⟩

Share

Metrics

Record views

113

Files downloads

138