Evolving Spiking Networks with Variable Resistive Memories

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. The results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types.

[1]  K. Stanković,et al.  Simulated Effects of Proton and Ion Beam Irradiation on Titanium Dioxide Memristors , 2010, IEEE Transactions on Nuclear Science.

[2]  Blaise MOUTTET Volgenau,et al.  Memristor Pattern Recognition Circuit Architecture for Robotics , 2009 .

[3]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[4]  Eytan Ruppin,et al.  Neural Processing of Counting in Evolved Spiking and McCulloch-Pitts Agents , 2006, Artificial Life.

[5]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[6]  Dario Floreano,et al.  Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs , 2003, EvoWorkshops.

[7]  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.

[8]  Damien Querlioz,et al.  Simulation of a memristor-based spiking neural network immune to device variations , 2011, The 2011 International Joint Conference on Neural Networks.

[9]  Andrea Soltoggio.  Neural Plasticity and Minimal Topologies for Reward-Based Learning , 2008, 2008 Eighth International Conference on Hybrid Intelligent Systems.

[10]  Brian Goldiez,et al.  A Survey of Commercial & Open Source Unmanned Vehicle Simulators , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[11]  Hisashi Shima,et al.  Resistive Random Access Memory (ReRAM) Based on Metal Oxides , 2010, Proceedings of the IEEE.

[12]  Ahmad Ayatollahi,et al.  STDP implementation using memristive nanodevice in CMOS-Nano neuromorphic networks , 2009, IEICE Electron. Express.

[13]  Olivier Michel,et al.  Cyberbotics Ltd. Webots™: Professional Mobile Robot Simulation , 2004, ArXiv.

[14]  Mathias Beike,et al.  Digital Integrated Circuits A Design Perspective , 2016 .

[15]  Risto Miikkulainen,et al.  Real-time neuroevolution in the NERO video game , 2005, IEEE Transactions on Evolutionary Computation.

[16]  Chris Christodoulou,et al.  Behavioral plasticity through the modulation of switch neurons , 2016, Neural Networks.

[17]  Ella. Gale.  The memory-conservation model of memristance , 2012 .

[18]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[19]  W. Alan Doolittle,et al.  Complementary oxide memristor technology facilitating both inhibitory and excitatory synapses for potential neuromorphic computing applications , 2009, 2009 International Semiconductor Device Research Symposium.

[20]  Andrew Adamatzky,et al.  The effect of electrode size on memristor properties: An experimental and theoretical study , 2012, 2012 IEEE International Conference on Electronics Design, Systems and Applications (ICEDSA).

[21]  Gregory S. Snider,et al.  Spike-timing-dependent learning in memristive nanodevices , 2008, 2008 IEEE International Symposium on Nanoscale Architectures.

[22]  R. Waser,et al.  Nanoionics-based resistive switching memories. , 2007, Nature materials.

[23]  G. Snider,et al.  Computing with hysteretic resistor crossbars , 2005 .

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

[25]  Y. Inoue,et al.  High Speed Unipolar Switching Resistance RAM (RRAM) Technology , 2006, 2006 International Electron Devices Meeting.

[26]  Larry Bull,et al.  A Neural Learning Classifier System with Self-Adaptive Constructivism for Mobile Robot Control , 2006, Artificial Life.

[27]  José Neves,et al.  Evolutionary Neural Network Learning , 2003, EPIA.

[28]  Dario Floreano,et al.  Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios , 2008, ALIFE.

[29]  Bernabé Linares-Barranco,et al.  Memristance can explain Spike-Time-Dependent-Plasticity in Neural Synapses , 2009 .

[30]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[31]  Wulfram Gerstner,et al.  Spiking Neuron Models: An Introduction , 2002 .

[32]  Alex A. Freitas,et al.  Evolutionary Computation , 2002 .

[33]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[34]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[35]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[36]  L. Chua.  Memristor-The missing circuit element , 1971 .

[37]  Peng Li,et al.  Nonvolatile memristor memory: Device characteristics and design implications , 2009, 2009 IEEE/ACM International Conference on Computer-Aided Design - Digest of Technical Papers.

[38]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[39]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[40]  Jiahai Wang,et al.  A binary Hopfield neural network with hysteresis for large crossbar packet-switches , 2005, Neurocomputing.

[41]  V. Erokhin,et al.  Electrochemically controlled polymeric device: a memristor (and more) found two years ago , 2008, 0807.0333.

[42]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

[43]  James A. Reggia,et al.  Evolutionary Design of Neural Network Architectures Using a Descriptive Encoding Language , 2006, IEEE Transactions on Evolutionary Computation.

[44]  Olivier Michel,et al.  Cyberbotics Ltd. Webots™: Professional Mobile Robot Simulation , 2004 .

[45]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[46]  L. Abbott,et al.  Synaptic computation , 2004, Nature.

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

[48]  Dario Floreano,et al.  Analog Genetic Encoding for the Evolution of Circuits and Networks , 2007, IEEE Transactions on Evolutionary Computation.

[49]  Dario Floreano,et al.  Evolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments , 2001, Evolutionary Computation.

[50]  Andrew Adamatzky,et al.  Different behaviour seen in flexible titanium dioxide sol-gel memristors dependent on the choice of electrode materials , 2012 .

[51]  Wolfgang Maass,et al.  Dynamic Stochastic Synapses as Computational Units , 1997, Neural Computation.

[52]  Massimiliano Di Ventra,et al.  Memristive model of amoeba learning. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[53]  Werner M. Kistler,et al.  Spike-timing dependent synaptic plasticity: a phenomenological framework , 2002, Biological Cybernetics.

[54]  Gerard David Howard.  Constructivist and spiking neural learning classifier systems , 2011 .

[55]  Andrew Adamatzky,et al.  Evolution of Plastic Learning in Spiking Networks via Memristive Connections , 2012, IEEE Transactions on Evolutionary Computation.

[56]  P. Durr,et al.  Evolvability of Neuromodulated Learning for Robots , 2008, 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS).