Growing Adaptive Machines
Combining Development and Learning in Artificial Neural Networks
Page
%P
-
Book
-
Chapter
Artificial Neurogenesis: An Introduction and Selective Review
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 de...
-
Article
Evolutionary design of soft-bodied animats with decentralized control
We show how a biologically inspired model of multicellular development combined with a simulated evolutionary process can be used to design the morphologies and controllers of soft-bodied virtual animats. An a...
-
Chapter and Conference Paper
Gardening Cyber-Physical Systems
Today’s artefacts, from small devices to buildings and cities, are, or are becoming, cyber-physical socio-technical systems, with tightly interwoven material and computational parts. Currently, we have to labo...
-
Chapter
Embryomorphic Engineering: Emergent Innovation Through Evolutionary Development
Embryomorphic Engineering, a particular instance of Morphogenetic Engineering, takes its inspiration directly from biological development to create new robotic, software or network architectures by decentralized ...
-
Chapter
Mechanisms for Complex Systems Engineering Through Artificial Development
We argue that artificial development is an appropriate means of approaching complex systems engineering. Artificial development works via the inclusion of mechanisms that enhance the evolvability of a design s...
-
Chapter
Image Processing and CGP
In this chapter, we will present three applications in which CGP can automatically generate novel image processing algorithms that compare to or exceed the best known conventional solutions. The applications f...
-
Chapter and Conference Paper
An Empirical Exploration of a Definition of Creative Novelty for Generative Art
We explore a new definition of creativity — one which emphasizes the statistical capacity of a system to generate previously unseen patterns — and discuss motivations for this perspective in the context of mac...
-
Chapter and Conference Paper
CellNet Co-Ev: Evolving Better Pattern Recognizers Using Competitive Co-evolution
A model for the co-evolution of patterns and classifiers is presented. The CellNet system for generating binary classifiers is used as a base for experimentation. The CellNet system is extended to include a co...
