Unsupervised features extraction from asynchronous silicon retina through Spike-Timing-Dependent Plasticity

In this paper, we present a novel approach to extract complex and overlapping temporally correlated features directly from spike-based dynamic vision sensors. A spiking neural network capable of performing multilayer unsupervised learning through Spike-Timing-Dependent Plasticity is introduced. It shows exceptional performances at detecting cars passing on a freeway recorded with a dynamic vision sensor, after only 10 minutes of fully unsupervised learning. Our methodology is thoroughly explained and first applied to a simpler example of ball trajectory learning. Two unsupervised learning strategies are investigated for advanced features learning. Robustness of our network to synaptic and neuron variability is assessed and virtual immunity to noise and jitter is demonstrated.

[1]  Eugene M. Izhikevich,et al.  Relating STDP to BCM , 2003, Neural Computation.

[2]  Y. Dan,et al.  Spike Timing-Dependent Plasticity of Neural Circuits , 2004, Neuron.

[3]  Sander M. Bohte,et al.  Reducing the Variability of Neural Responses: A Computational Theory of Spike-Timing-Dependent Plasticity , 2007, Neural Computation.

[4]  Timothée Masquelier,et al.  Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity , 2007, PLoS Comput. Biol..

[5]  Rufin VanRullen,et al.  Temporal codes and sparse representations: A key to understanding rapid processing in the visual system , 2004, Journal of Physiology-Paris.

[6]  Wolfgang Maass,et al.  STDP enables spiking neurons to detect hidden causes of their inputs , 2009, NIPS.

[7]  Tobias Delbrück,et al.  Frame-free dynamic digital vision , 2008 .

[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]  Tobi Delbrück,et al.  A 128$\times$ 128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor , 2008, IEEE Journal of Solid-State Circuits.

[10]  Bernabé Linares-Barranco,et al.  Spike-Based Convolutional Network for Real-Time Processing , 2010, 2010 20th International Conference on Pattern Recognition.

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

[12]  Lyle N. Long,et al.  Character Recognition using Spiking Neural Networks , 2007, 2007 International Joint Conference on Neural Networks.

[13]  W. Lu,et al.  High-density crossbar arrays based on a Si memristive system. , 2009, Nano letters.

[14]  D. Johnston,et al.  Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs , 1997 .

[15]  S. Thorpe,et al.  Spike Timing Dependent Plasticity Finds the Start of Repeating Patterns in Continuous Spike Trains , 2008, PloS one.

[16]  T. Delbruck,et al.  > Replace This Line with Your Paper Identification Number (double-click Here to Edit) < 1 , 2022 .

[17]  Timothée Masquelier,et al.  Competitive STDP-Based Spike Pattern Learning , 2009, Neural Computation.

[18]  Kwabena Boahen,et al.  Optic nerve signals in a neuromorphic chip I: Outer and inner retina models , 2004, IEEE Transactions on Biomedical Engineering.