Simplified spiking neural network architecture and STDP learning algorithm applied to image classification

Spiking neural networks (SNN) have gained popularity in embedded applications such as robotics and computer vision. The main advantages of SNN are the temporal plasticity, ease of use in neural interface circuits and reduced computation complexity. SNN have been successfully used for image classification. They provide a model for the mammalian visual cortex, image segmentation and pattern recognition. Different spiking neuron mathematical models exist, but their computational complexity makes them ill-suited for hardware implementation. In this paper, a novel, simplified and computationally efficient model of spike response model (SRM) neuron with spike-time dependent plasticity (STDP) learning is presented. Frequency spike coding based on receptive fields is used for data representation; images are encoded by the network and processed in a similar manner as the primary layers in visual cortex. The network output can be used as a primary feature extractor for further refined recognition or as a simple object classifier. Results show that the model can successfully learn and classify black and white images with added noise or partially obscured samples with up to ×20 computing speed-up at an equivalent classification ratio when compared to classic SRM neuron membrane models. The proposed solution combines spike encoding, network topology, neuron membrane model and STDP learning.

[1]  Johannes Schemmel,et al.  Live demonstration: A scaled-down version of the BrainScaleS wafer-scale neuromorphic system , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[2]  Y. Ishikawa,et al.  A neuron MOS variable logic circuit with the simplified circuit structure , 2004, Proceedings of 2004 IEEE Asia-Pacific Conference on Advanced System Integrated Circuits.

[3]  Krzysztof J. Cios,et al.  A spiking neural network alternative for the analog to digital converter , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[4]  Bernabé Linares-Barranco,et al.  Fast Vision Through Frameless Event-Based Sensing and Convolutional Processing: Application to Texture Recognition , 2010, IEEE Transactions on Neural Networks.

[5]  Amine Bermak,et al.  A Spiking Neural Network for Gas Discrimination Using a Tin Oxide Sensor Array , 2008, 4th IEEE International Symposium on Electronic Design, Test and Applications (delta 2008).

[6]  Jim D. Garside,et al.  SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network Simulation , 2013, IEEE Journal of Solid-State Circuits.

[7]  T. Martin McGinnity,et al.  A spiking neural network for tactile form based object recognition , 2011, The 2011 International Joint Conference on Neural Networks.

[8]  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.

[9]  J. Alonso,et al.  Complex Receptive Fields in Primary Visual Cortex , 2003, The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry.

[10]  Grzegorz Rozenberg,et al.  Handbook of Natural Computing , 2011, Springer Berlin Heidelberg.

[11]  Colin D. Simpson,et al.  Industrial Electronics , 1936, Nature.

[12]  Tarek M. Taha,et al.  FPGA Implementation of Izhikevich Spiking Neural Networks for Character Recognition , 2009, 2009 International Conference on Reconfigurable Computing and FPGAs.

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

[14]  R. Lorenzo,et al.  A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[15]  Ricardo Silva,et al.  The neuroid: A novel and simplified neuron-model , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Murray Shanahan,et al.  Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[17]  Tong Tang,et al.  Proceedings of the European Symposium on Artificial Neural Networks , 2006 .

[18]  Sander M. Bohte,et al.  Computing with Spiking Neuron Networks , 2012, Handbook of Natural Computing.

[19]  Benjamin Schrauwen,et al.  Parallel hardware implementation of a broad class of spiking neurons using serial arithmetic , 2006, ESANN.

[20]  D.T. Pham,et al.  A self-organising spiking neural network trained using delay adaptation , 2007, 2007 IEEE International Symposium on Industrial Electronics.

[21]  Takenori Obo,et al.  Human gesture recognition for robot partners by spiking neural network and classification learning , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.

[22]  Tim Schönauer,et al.  NeuroPipe-Chip: A digital neuro-processor for spiking neural networks , 2002, IEEE Trans. Neural Networks.

[23]  Bernabé Linares-Barranco,et al.  Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate Coding and Coincidence Processing--Application to Feedforward ConvNets , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Kazuyuki Murase,et al.  Sensor-fusion in spiking neural network that generates autonomous behavior in real mobile robot , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

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

[26]  Yongji Wang,et al.  Spiking Neural Networks for Cortical Neuronal Spike Train Decoding , 2010, Neural Computation.

[27]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[28]  Olaf Booij,et al.  Temporal Pattern Classification using Spiking Neural Networks , 2004 .

[29]  Austin J. Brockmeier,et al.  Evaluating dependence in spike train metric spaces , 2011, The 2011 International Joint Conference on Neural Networks.

[30]  Mark C. W. van Rossum,et al.  Stable Hebbian Learning from Spike Timing-Dependent Plasticity , 2000, The Journal of Neuroscience.