On Why Artificial Neural Networks should be Developmental.

Biological brains are capable of general learning without super- vision. This is learning across mutiple domains without interference. Unlike artificial neural networks, in real brains, learned information is not purely en- coded in real-valued weights but instead it is resides in many neural aspects. Such aspects include, dendritic and axonal morphology, number and location of synapses, synaptic strengths and the internal state of neural components. Natural evolution has come up with extraordinary 'programs' for neurons that allow them to build learning systems through group activity. The neuron is the 'brain within the brain'. We argue that evolving neural developmental programs which when executed continuously build, shape and adjust neural networks is a promising direction for future research. We discuss aspects of neu- roscience that are important, and examine a model that incorporates many of these features that has been applied to a number of problems: wumpus world, checkers and maze solving.

[1]  Peter J. Bentley,et al.  On growth, form and computers , 2003 .

[2]  Kenneth O. Stanley,et al.  Compositional Pattern Producing Networks : A Novel Abstraction of Development , 2007 .

[3]  Dominique Debanne,et al.  Brain plasticity and ion channels , 2003, Journal of Physiology-Paris.

[4]  Keith L. Downing,et al.  Supplementing evolutionary developmental systems with abstract models of neurogenesis , 2007, GECCO '07.

[5]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[6]  Julian Francis Miller.  Cartesian Genetic Programming , 2011, Cartesian Genetic Programming.

[7]  N. Jakobi.  21 – Harnessing morphogenesis , 2003 .

[8]  T. Bliss,et al.  Long‐lasting potentiation of synaptic transmission in the dentate area of the anaesthetized rabbit following stimulation of the perforant path , 1973, The Journal of physiology.

[9]  Gul Muhammad Khan,et al.  Solving Mazes using an Artificial Developmental Neuron , 2010, ALIFE.

[10]  U. Frey,et al.  Synaptic tagging and long-term potentiation , 1997, Nature.

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

[12]  Arjen Van Ooyen,et al.  Modeling neural development , 2003 .

[13]  Wulfram Gerstner,et al.  Spiking Neuron Models , 2002 .

[14]  T. Bliss,et al.  Plasticity in the human central nervous system. , 2006, Brain : a journal of neurology.

[15]  J. Kleim,et al.  Synaptogenesis and FOS Expression in the Motor Cortex of the Adult Rat after Motor Skill Learning , 1996, The Journal of Neuroscience.

[16]  F. Valverde,et al.  Rate and extent of recovery from dark rearing in the visual cortex of the mouse. , 1971, Brain research.

[17]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

[18]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[19]  A. V. Ooyen,et al.  Activity-dependent outgrowth of neurons and overshoot phenomena in developing neural networks , 1994 .

[20]  Richard S. J. Frackowiak,et al.  Navigation-related structural change in the hippocampi of taxi drivers. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[21]  T. Sejnowski,et al.  Irresistible environment meets immovable neurons , 1997, Behavioral and Brain Sciences.

[22]  R. French,et al.  Catastrophic Forgetting in Connectionist Networks: Causes, Consequences and Solutions , 1994 .

[23]  D. Ballard,et al.  Learning-Dependent Synaptic Modifications in the Cerebellar Cortex of the Adult Rat Persist for at Least Four Weeks , 1997, The Journal of Neuroscience.

[24]  Jordan B. Pollack,et al.  TITLE : Generative Representations for the Automated Design of Modular Physical Robots , 2003 .

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

[26]  S. Quartz.  The constructivist brain , 1999, Trends in Cognitive Sciences.

[27]  Eliot A. Brenowitz,et al.  Seasonal plasticity in the adult brain , 2000, Trends in Neurosciences.

[28]  Federico Bermúdez-Rattoni,et al.  Neural Plasticity and Memory , 2007 .

[29]  M. Sheng,et al.  Molecular mechanisms of dendritic spine morphogenesis , 2006, Current Opinion in Neurobiology.

[30]  A. Dekaban,et al.  Changes in brain weights during the span of human life: Relation of brain weights to body heights and body weights , 1978, Annals of neurology.

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

[32]  M. Segal.  Dendritic spines and long-term plasticity , 2005, Nature Reviews Neuroscience.

[33]  Patrick D. Roberts,et al.  Spike timing dependent synaptic plasticity in biological systems , 2002, Biological Cybernetics.

[34]  M. Aminoff.  Principles of Neural Science. 4th edition , 2001 .

[35]  Eric B. Baum,et al.  A Proposal for More Powerful Learning Algorithms , 1989, Neural Computation.

[36]  Alistair G. Rust,et al.  Evolutionary neural topiary: growing and sculpting artifical neurons to order , 2000 .

[37]  Gul Muhammad Khan,et al.  Evolution of cartesian genetic programs capable of learning , 2009, GECCO '09.

[38]  Y. Ben-Ari,et al.  Long-term plasticity at GABAergic and glycinergic synapses: mechanisms and functional significance , 2002, Trends in Neurosciences.

[39]  Gul Muhammad Khan,et al.  Coevolution of intelligent agents using cartesian genetic programming , 2007, GECCO '07.

[40]  S. Rose,et al.  The Making of Memory: From Molecules to Mind , 1996 .

[41]  J. Stephen Judd,et al.  On the complexity of loading shallow neural networks , 1988, J. Complex..

[42]  Francis Crick,et al.  The recent excitement about neural networks , 1989, Nature.

[43]  James L. McClelland,et al.  Connectionist models of development , 2003 .

[44]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

[45]  M. Alexander,et al.  Principles of Neural Science , 1981 .

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

[47]  John Raymond Smythies.  The Dynamic Neuron , 2002 .

[48]  Marcus Frean,et al.  The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks , 1990, Neural Computation.

[49]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[50]  A. Cangelosi,et al.  Cell division and migration in a 'genotype' for neural networks (Cell division and migration in neural networks) , 1993 .

[51]  Christof Koch,et al.  Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series) , 1998 .

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

[53]  G. Shepherd.  The Synaptic Organization of the Brain , 1979 .

[54]  Philip T. Quinlan,et al.  Structural change and development in real and artificial neural networks , 1998, Neural Networks.

[55]  Gregory S. Hornby,et al.  Body-brain co-evolution using L-systems as a generative encoding , 2001 .