Artificial Neurogenesis: An Introduction and Selective Review

Taras Kowaliw (1) , Nicolas Bredeche (2, 3) , Sylvain Chevallier (4) , René Doursat (5)

1 ISC-PIF - Institut des Systèmes Complexes - Paris Ile-de-France
2 ISIR - Institut des Systèmes Intelligents et de Robotique
3 AMAC
4 LISV - Laboratoire d'Ingénierie des Systèmes de Versailles
5 Drexel University

In this introduction and review—like in the book which follows—we explore the hypothesis that adaptive growth is a means of producing brain-like machines. The emulation of neural development can incorporate desirable characteristics of natural neural systems into engineered designs. The introduction begins with a review of neural development and neural models. Next, artificial development— the use of a developmentally-inspired stage in engineering design—is introduced. Several strategies for performing this " meta-design " for artificial neural systems are reviewed. This work is divided into three main categories: bio-inspired representations ; developmental systems; and epigenetic simulations. Several specific network biases and their benefits to neural network design are identified in these contexts. In particular, several recent studies show a strong synergy, sometimes interchange-ability, between developmental and epigenetic processes—a topic that has remained largely under-explored in the literature.

Mots clés: Neural models; Adaptive growth; Artificial neurogenesis; Developmental systems; Bio-inspiration; Epigenetic simulations

Domaines: Intelligence artificielle [cs.AI]; Modélisation et simulation; Réseau de neurones [cs.NE]; Sciences cognitives; Neurosciences

Taras Kowaliw, Nicolas Bredeche, Sylvain Chevallier, René Doursat. Artificial Neurogenesis: An Introduction and Selective Review. Springer; Taras Kowaliw, Nicolas Bredeche, René Doursat. Growing Adaptive Machines, 557, pp.1-60, 2014, Studies in Computational Intelligence, 978-3-642-55336-3. ⟨10.1007/978-3-642-55337-0_1⟩. ⟨hal-01351738⟩