Spiking-timing based pattern recognition with real-world visual stimuli

Pattern recognition has been widely studied in the field of computational intelligence. However, primates outperform existing algorithms in cognitive tasks without any difficulty and most of current methods lack enough biological plausibility. Inspired by recent biological findings, a spike-timing based computational model is described, in which information is represented by temporal codes with explicit firing times rather than firing rates of neurons. Visual stimulation is converted into precisely timed spikes by a retina-like model. Encoded spatiotemporal patterns are learned by a temporal learning algorithm based on spiking-timing-dependent plasticity (STDP). The computational model integrates encoding and learning with a unified neural representation closing the gap between them. We show that our integrated model is capable of recognizing real world stimuli such as images successfully with fast and efficient neural computation.

[1]  E. D. Adrian,et al.  The Basis of Sensation , 1928, The Indian Medical Gazette.

[2]  Carlos D. Brody,et al.  Simple Networks for Spike-Timing-Based Computation, with Application to Olfactory Processing , 2003, Neuron.

[3]  E. Knudsen.  Supervised learning in the brain , 1994, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[4]  Glenn C. Turner,et al.  Oscillations and Sparsening of Odor Representations in the Mushroom Body , 2002, Science.

[5]  D. Sagi,et al.  Dynamics of Memory Representations in Networks with Novelty-Facilitated Synaptic Plasticity , 2006, Neuron.

[6]  J. Knott.  The organization of behavior: A neuropsychological theory , 1951 .

[7]  Tim Gollisch,et al.  Rapid Neural Coding in the Retina with Relative Spike Latencies , 2008, Science.

[8]  Zoltan Nadasdy,et al.  Information Encoding and Reconstruction from the Phase of Action Potentials , 2009, Front. Syst. Neurosci..

[9]  S. Thorpe,et al.  Spike times make sense , 2005, Trends in Neurosciences.

[10]  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.

[11]  Walter Senn,et al.  Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics , 2007, Neural Computation.

[12]  R. Johansson,et al.  First spikes in ensembles of human tactile afferents code complex spatial fingertip events , 2004, Nature Neuroscience.

[13]  N. Logothetis,et al.  Millisecond encoding precision of auditory cortex neurons , 2010, Proceedings of the National Academy of Sciences.

[14]  D. Bodznick,et al.  Error-driven motor learning in fish. , 2002, The Biological bulletin.

[15]  Sander M. Bohte,et al.  Error-backpropagation in temporally encoded networks of spiking neurons , 2000, Neurocomputing.

[16]  M. Greschner,et al.  Complex spike-event pattern of transient ON-OFF retinal ganglion cells. , 2006, Journal of neurophysiology.

[17]  F. Esposti,et al.  In vivo evidence that retinal bipolar cells generate spikes modulated by light , 2011, Nature Neuroscience.

[18]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

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

[20]  Masao Ito.  Mechanisms of motor learning in the cerebellum 1 1 Published on the World Wide Web on 24 November 2000. , 2000, Brain Research.

[21]  Michael J. Berry,et al.  The structure and precision of retinal spike trains. , 1997, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Terumine Hayashi,et al.  Obstacle to training SpikeProp networks — Cause of surges in training process — , 2009, 2009 International Joint Conference on Neural Networks.

[23]  Paul H. E. Tiesinga,et al.  A New Correlation-Based Measure of Spike Timing Reliability , 2002, Neurocomputing.

[24]  F. Mechler,et al.  Temporal coding of contrast in primary visual cortex: when, what, and why. , 2001, Journal of neurophysiology.

[25]  B J Richmond,et al.  Stochastic nature of precisely timed spike patterns in visual system neuronal responses. , 1999, Journal of neurophysiology.

[26]  Andrzej J. Kasinski,et al.  Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting , 2010, Neural Computation.

[27]  C E Carr,et al.  Processing of temporal information in the brain. , 1993, Annual review of neuroscience.

[28]  G. Bi,et al.  Synaptic modification by correlated activity: Hebb's postulate revisited. , 2001, Annual review of neuroscience.

[29]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[30]  Masao Ito.  Control of mental activities by internal models in the cerebellum , 2008, Nature Reviews Neuroscience.

[31]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[32]  J J Hopfield,et al.  What is a moment? Transient synchrony as a collective mechanism for spatiotemporal integration. , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[33]  B. Richmond,et al.  Latency: another potential code for feature binding in striate cortex. , 1996, Journal of neurophysiology.

[34]  F. Esposti,et al.  Spikes in Retinal Bipolar Cells Phase-Lock to Visual Stimuli with Millisecond Precision , 2011, Current Biology.