Learning at the edge of chaos : Temporal Coupling of Spiking Neurons Controller for Autonomous Robotic

In this paper, a recurrent spiking neural networks is trained on an robot to learn to avoid obstacles using visual flow. At the starting of the process, this network is initialized in a ”chaotic” state and a STDP-like learning algorithm is used. We argue that a proper scaling variable can direct the network from chaos to synchronized state and back. This process allows us to train the robot because it links (external) temporal loops with (internal) neural activity. We use the scaling factor to have this coupling functional. Given an over-simplistic scaling, we managed to obtain very interesting resulting behaviors when tested on a real

[1]  E. Adrian,et al.  The impulses produced by sensory nerve endings , 1926, The Journal of physiology.

[2]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[3]  Christopher G. Langton,et al.  Computation at the edge of chaos: Phase transitions and emergent computation , 1990 .

[4]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[5]  W. Singer.  Synchronization of cortical activity and its putative role in information processing and learning. , 1993, Annual review of physiology.

[6]  J. Rinzel,et al.  Clustering in globally coupled inhibitory neurons , 1994 .

[7]  Eytan Domany,et al.  Temporal aspects of coding and information processing in biological systems , 1994 .

[8]  J. J. Hopfield,et al.  Pattern recognition computation using action potential timing for stimulus representation , 1995, Nature.

[9]  Denis Fize,et al.  Speed of processing in the human visual system , 1996, Nature.

[10]  H. Sompolinsky,et al.  Chaos in Neuronal Networks with Balanced Excitatory and Inhibitory Activity , 1996, Science.

[11]  Simon J. Thorpe,et al.  Implementing Hebbian Learning in a Rank-Based Neural Network , 1997, ICANN.

[12]  H. Markram,et al.  Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs , 1997, Science.

[13]  Carson C. Chow.  Phase-locking in weakly heterogeneous neuronal networks , 1997, cond-mat/9709220.

[14]  G. Bi,et al.  Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type , 1998, The Journal of Neuroscience.

[15]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[16]  C. Gray.  The Temporal Correlation Hypothesis of Visual Feature Integration Still Alive and Well , 1999, Neuron.

[17]  Wulfram Gerstner.  Populations of spiking neurons , 1999 .

[18]  Maurizio Mattia,et al.  Collective Behavior of Networks with Linear (VLSI) Integrate-and-Fire Neurons , 1999, Neural Computation.

[19]  L. Abbott,et al.  Synaptic plasticity: taming the beast , 2000, Nature Neuroscience.

[20]  Mathias Quoy,et al.  Random Recurrent Neural Networks for Autonomous System Design , 2000 .

[21]  Stephen Coombes.  Chaos in integrate-and-fire dynamical systems , 2000 .

[22]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[23]  J. Martinerie,et al.  The brainweb: Phase synchronization and large-scale integration , 2001, Nature Reviews Neuroscience.

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

[25]  M. Mattia,et al.  Population dynamics of interacting spiking neurons. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[26]  Carl van Vreeswijk,et al.  Temporal Correlations in Stochastic Networks of Spiking Neurons , 2002, Neural Computation.

[27]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[28]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[29]  Ezequiel A. Di Paolo,et al.  Evolving spike-timing-dependent plasticity for single-trial learning in robots , 2003 .

[30]  Joël Favrel,et al.  Evolving spiking neurons nets to control an animat , 2003, ICANNGA.

[31]  Nicolas Brunel,et al.  Dynamics of Sparsely Connected Networks of Excitatory and Inhibitory Spiking Neurons , 2000, Journal of Computational Neuroscience.