Dear all,

Some of you will be interested in our recent book, Growing Adaptive Machines: Combining Development and Learning in Artificial Neural Networks. 

The topic is the generation of low-level neural network architectures using bio-inspired models and simulations. By emulating the biological process of development, we can incorporate desirable characteristics of natural neural systems into engineered designs and thus move closer towards the creation of brain-like systems. 

The book includes two broad reviews, summaries of research portfolios from established researchers, and new research contributions. We believe it will form a valuable reference for advanced students and practitioners. See below for the table of contents. 

Best regards, 

Taras Kowaliw, Nicolas Bredeche, René Doursat (Editors)

=-=-=-=-=

Table of Contents

Artificial Neurogenesis: An Introduction and Selective Review.  

T. Kowaliw, N. Bredeche, S. Chevallier and R. Doursat

A Brief Introduction to Probabilistic Machine Learning and Its Relation to Neuroscience.

T. Trappenberg

Evolving Culture Versus Local Minima.

Y. Bengio

Learning Sparse Features with an Auto-Associator. 

S. Rebecchi, H. Paugam-Moisy and M. Sebag

HyperNEAT: The First Five Years.

D. D’Ambrosio, J. Gauci and K. Stanley

Using the Genetic Regulatory Evolving Artificial Networks (GReaNs) Platform for Signal Processing, Animat Control, and Artificial Multicellular Development.

B. Wróbel and M. Joachimczak

Constructing Complex Systems Via Activity-Driven Unsupervised Hebbian Self-Organization

J. Bednar

Neuro-Centric and Holocentric Approaches to the Evolution of Developmental Neural Networks.

J. Miller

Artificial Evolution of Plastic Neural Networks: A Few Key Concepts.

J.-B. Mouret and P. Tonelli