Exploiting Regularity Without Development

A major challenge in evolutionary computation is to find the right level of abstraction of biological development to capture its essential properties without introducing unnecessary inefficiencies. In this paper, a novel abstraction of natural development, called Compositional Pattern Producing Networks (CPPNs), is proposed. Unlike most computational abstractions of natural development, CPPNs do not include a developmental phase, differentiating them from developmental encodings. Instead of development, CPPNs employ compositions of functions derived from gradient patterns present in developing natural organisms. In this paper, a variant of the NeuroEvolution of Augmenting Topologies (NEAT) method, called CPPN-NEAT, evolves increasingly complex CPPNs, producing patterns with strikingly natural characteristics.

[1]  A. Turing.  The chemical basis of morphogenesis , 1952, Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences.

[2]  Grace Jordison.  Molecular Biology of the Gene , 1965, The Yale Journal of Biology and Medicine.

[3]  A. Lindenmayer.  Mathematical models for cellular interactions in development. II. Simple and branching filaments with two-sided inputs. , 1968, Journal of theoretical biology.

[4]  Jeffrey W. Roberts,et al.  遺伝子の分子生物学 = Molecular biology of the gene , 1970 .

[5]  H. Meinhardt.  Models of biological pattern formation , 1982 .

[6]  R. Dawkins.  The Blind Watchmaker , 1986 .

[7]  A. Turing,et al.  The chemical basis of morphogenesis. 1953. , 1990, Bulletin of mathematical biology.

[8]  Karl Sims,et al.  Artificial evolution for computer graphics , 1991, SIGGRAPH.

[9]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[10]  Lee Altenberg,et al.  Evolving better representations through selective genome growth , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[11]  Karl Sims,et al.  Evolving 3D Morphology and Behavior by Competition , 1994, Artificial Life.

[12]  Karl Sims,et al.  Evolving 3d morphology and behavior by competition , 1994 .

[13]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[14]  D. Curtis,et al.  nanos is an evolutionarily conserved organizer of anterior-posterior polarity. , 1995, Development.

[15]  David B. Fogel,et al.  Evolving Neural Control Systems , 1995, IEEE Expert.

[16]  Maja J. Matarić,et al.  A Developmental Model for the Evolution of Complete Autonomous Agents , 1996 .

[17]  Larry D. Pyeatt,et al.  A comparison between cellular encoding and direct encoding for genetic neural networks , 1996 .

[18]  R. Raff.  Understanding Evolution: The Next Step. (Book Reviews: The Shape of Life. Genes, Development, and the Evolution of Animal Form.) , 1996 .

[19]  Andrew P. Martin.  Increasing Genomic Complexity by Gene Duplication and the Origin of Vertebrates , 1999, The American Naturalist.

[20]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[21]  Risto Miikkulainen,et al.  Solving Non-Markovian Control Tasks with Neuro-Evolution , 1999, IJCAI.

[22]  Peter J. Bentley,et al.  Three Ways to Grow Designs: A Comparison of Evolved Embryogenies for a Design Problem , 1999 .

[23]  Christoph Adami,et al.  A Developmental Model for the Evolution of Artificial Neural Networks , 2000, Artificial Life.

[24]  Julian Francis Miller,et al.  Cartesian genetic programming , 2000, GECCO '10.

[25]  S. Lall,et al.  Conservation and divergence in molecular mechanisms of axis formation. , 2001, Annual review of genetics.

[26]  Hideyuki Takagi,et al.  Interactive evolutionary computation: fusion of the capabilities of EC optimization and human evaluation , 2001, Proc. IEEE.

[27]  Jordan B. Pollack,et al.  Creating High-Level Components with a Generative Representation for Body-Brain Evolution , 2002, Artificial Life.

[28]  Josh Bongard,et al.  Evolving modular genetic regulatory networks , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[29]  S. Carroll,et al.  Gene co-option in physiological and morphological evolution. , 2002, Annual review of cell and developmental biology.

[30]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[31]  R. Beer,et al.  20 – A developmental model for the evolution of complete autonomous agents , 2003 .

[32]  Risto Miikkulainen,et al.  A Taxonomy for Artificial Embryogeny , 2003, Artificial Life.

[33]  Dirk Thierens,et al.  Exploiting Modularity, Hierarchy, and Repetition in Variable-Length Problems , 2004, GECCO.

[34]  Risto Miikkulainen,et al.  Competitive Coevolution through Evolutionary Complexification , 2011, J. Artif. Intell. Res..

[35]  Daniel Roggen,et al.  Multi-cellular Development: Is There Scalability and Robustness to Gain? , 2004, PPSN.

[36]  S. Vijayakumar,et al.  Evolving a neurocontroller through a process of embryogeny , 2004 .

[37]  Julian Francis Miller,et al.  Evolving a Self-Repairing, Self-Regulating, French Flag Organism , 2004, GECCO.

[38]  Tim Andersen,et al.  A biologically derived approach to tissue modeling. , 2005, Studies in health technology and informatics.

[39]  Nicholas J. Radcliffe,et al.  Genetic set recombination and its application to neural network topology optimisation , 1993, Neural Computing & Applications.

[40]  Kenneth O. Stanley.  Comparing Artificial Phenotypes with Natural Biological Patterns , 2006 .

[41]  D. McCandless.  Fundamental neuroscience , 1997, Metabolic Brain Disease.