Artificial Evolution of Plastic Neural Networks: a few Key Concepts

Abstract : This paper introduces a hierarchy of concepts to classify the goals and the methods of works that mix neuro-evolution and synaptic plasticity. We propose definitions of “behavioral robustness” and oppose it to “reward-based behavioral changes”; we then distinguish the switch between behaviors and the acquisition of new behaviors. Last, we formalize the concept of “synaptic General Learning Abilities” (sGLA) and that of “synaptic Transitive Learning Abilities (sTLA)”. For each concept, we review the literature to identify the main experimental setups and the typical studies.
Document type :
Book sections
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download
Contributor : Jean-Baptiste Mouret <>
Submitted on : Monday, April 11, 2016 - 10:34:15 PM
Last modification on : Thursday, March 21, 2019 - 1:21:06 PM
Long-term archiving on : Monday, November 14, 2016 - 11:37:40 PM


Files produced by the author(s)


  • HAL Id : hal-01300702, version 1


Jean-Baptiste Mouret, Paul Tonelli. Artificial Evolution of Plastic Neural Networks: a few Key Concepts. Taras Kowaliw, Nicolas Bredeche, René Doursat. Growing Adaptive Machines: combining Development and Learning in Artificial Neural Networks, 557, Springer, pp.251-261, 2014, 978-3-642-55336-3. ⟨⟩. ⟨hal-01300702⟩



Record views


Files downloads