Connection and Coordination: The Interplay Between Architecture and Dynamics in Evolved Model Pattern Generators

We undertake a systematic study of the role of neural architecture in shaping the dynamics of evolved model pattern generators for a walking task. First, we consider the minimum number of connections necessary to achieve high performance on this task. Next, we identify architectural motifs associated with high fitness. We then examine how high-fitness architectures differ in their ability to evolve. Finally, we demonstrate the existence of distinct parameter subgroups in some architectures and show that these subgroups are characterized by differences in neuron excitabilities and connection signs.

[1]  Patrick D. Roberts,et al.  Classification of Temporal Patterns in Dynamic Biological Networks , 1998, Neural Computation.

[2]  Jean-Arcady Meyer,et al.  Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects , 1998, IEEE Trans. Neural Networks.

[3]  E. Marder,et al.  Principles of rhythmic motor pattern generation. , 1996, Physiological reviews.

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

[5]  Jürgen Kurths,et al.  Synchronization - A Universal Concept in Nonlinear Sciences , 2001, Cambridge Nonlinear Science Series.

[6]  Randall D. Beer,et al.  Parameter Space Structure of Continuous-Time Recurrent Neural Networks , 2006, Neural Computation.

[7]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[8]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[9]  S. Schuster,et al.  Metabolic network structure determines key aspects of functionality and regulation , 2002, Nature.

[10]  P. Bourgine,et al.  Topological and causal structure of the yeast transcriptional regulatory network , 2002, Nature Genetics.

[11]  G Tononi,et al.  Theoretical neuroanatomy: relating anatomical and functional connectivity in graphs and cortical connection matrices. , 2000, Cerebral cortex.

[12]  S. Strogatz.  Exploring complex networks , 2001, Nature.

[13]  Frank Harary,et al.  Graph Theory , 2016 .

[14]  Albert-László Barabási,et al.  Error and attack tolerance of complex networks , 2000, Nature.

[15]  R. Albert,et al.  The large-scale organization of metabolic networks , 2000, Nature.

[16]  Marcus Pivato,et al.  Symmetry Groupoids and Patterns of Synchrony in Coupled Cell Networks , 2003, SIAM J. Appl. Dyn. Syst..

[17]  Guido Caldarelli,et al.  Universal scaling relations in food webs , 2003, Nature.

[18]  Thomas Bäck,et al.  Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms , 1996 .

[19]  Charles F. Stevens,et al.  How Cortical Interconnectedness Varies with Network Size , 1989, Neural Computation.

[20]  Frank Pasemann,et al.  Reflex-oscillations in evolved single leg neurocontrollers for walking machines , 2007, Natural Computing.

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

[22]  D C Van Essen,et al.  Information processing in the primate visual system: an integrated systems perspective. , 1992, Science.

[23]  S. Shen-Orr,et al.  Network motifs: simple building blocks of complex networks. , 2002, Science.

[24]  Frédéric Gruau,et al.  Automatic Definition of Modular Neural Networks , 1994, Adapt. Behav..

[25]  Valentino Braitenberg,et al.  Brain Size and Number of Neurons: An Exercise in Synthetic Neuroanatomy , 2004, Journal of Computational Neuroscience.

[26]  Randall D. Beer,et al.  Evolution and Analysis of Model CPGs for Walking: II. General Principles and Individual Variability , 1999, Journal of Computational Neuroscience.

[27]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

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

[29]  Thomas Bäck,et al.  Evolutionary Algorithms in Theory and Practice , 1996 .

[30]  P A Getting,et al.  Emerging principles governing the operation of neural networks. , 1989, Annual review of neuroscience.

[31]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[32]  Randall D. Beer,et al.  Evolution and Analysis of Model CPGs for Walking: I. Dynamical Modules , 1999, Journal of Computational Neuroscience.

[33]  Mark E. J. Newman,et al.  The Structure and Function of Complex Networks , 2003, SIAM Rev..