Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity

Spike timing dependent plasticity (STDP) is a learning rule that modifies synaptic strength as a function of the relative timing of pre- and postsynaptic spikes. When a neuron is repeatedly presented with similar inputs, STDP is known to have the effect of concentrating high synaptic weights on afferents that systematically fire early, while postsynaptic spike latencies decrease. Here we use this learning rule in an asynchronous feedforward spiking neural network that mimics the ventral visual pathway and shows that when the network is presented with natural images, selectivity to intermediate-complexity visual features emerges. Those features, which correspond to prototypical patterns that are both salient and consistently present in the images, are highly informative and enable robust object recognition, as demonstrated on various classification tasks. Taken together, these results show that temporal codes may be a key to understanding the phenomenal processing speed achieved by the visual system and that STDP can lead to fast and selective responses.

[1]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2]  Simon J. Thorpe,et al.  Spike arrival times: A highly efficient coding scheme for neural networks , 1990 .

[3]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

[4]  S. Thorpe,et al.  Dynamics of orientation coding in area V1 of the awake primate , 1993, Visual Neuroscience.

[5]  Keiji Tanaka,et al.  Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. , 1994, Journal of neurophysiology.

[6]  David I. Perrett,et al.  Modeling visual recognition from neurobiological constraints , 1994, Neural Networks.

[7]  Pieter R. Roelfsema,et al.  How Precise is Neuronal Synchronization? , 1995, Neural Computation.

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

[9]  N. Logothetis,et al.  Shape representation in the inferior temporal cortex of monkeys , 1995, Current Biology.

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

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

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

[13]  E. Rolls,et al.  INVARIANT FACE AND OBJECT RECOGNITION IN THE VISUAL SYSTEM , 1997, Progress in Neurobiology.

[14]  J Gautrais,et al.  Rate coding versus temporal order coding: a theoretical approach. , 1998, Bio Systems.

[15]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[16]  Li I. Zhang,et al.  A critical window for cooperation and competition among developing retinotectal synapses , 1998, Nature.

[17]  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.

[18]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

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

[20]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

[21]  D. Hubel,et al.  Microsaccadic eye movements and firing of single cells in the striate cortex of macaque monkeys , 2000, Nature Neuroscience.

[22]  Edmund T. Rolls,et al.  Position invariant recognition in the visual system with cluttered environments , 2000, Neural Networks.

[23]  Edmund T. Rolls,et al.  A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition, and Information-Based Performance Measures , 2000, Neural Computation.

[24]  D. Feldman,et al.  Timing-Based LTP and LTD at Vertical Inputs to Layer II/III Pyramidal Cells in Rat Barrel Cortex , 2000, Neuron.

[25]  Rufin van Rullen,et al.  Rate Coding Versus Temporal Order Coding: What the Retinal Ganglion Cells Tell the Visual Cortex , 2001, Neural Computation.

[26]  Arnaud Delorme,et al.  Networks of integrate-and-fire neurons using Rank Order Coding B: Spike timing dependent plasticity and emergence of orientation selectivity , 2001, Neurocomputing.

[27]  N. Sigala,et al.  Visual categorization shapes feature selectivity in the primate temporal cortex , 2002, Nature.

[28]  Robert A. Frazor,et al.  Visual cortex neurons of monkeys and cats: temporal dynamics of the contrast response function. , 2002, Journal of neurophysiology.

[29]  Gustavo Deco,et al.  Computational neuroscience of vision , 2002 .

[30]  Michel Vidal-Naquet,et al.  Visual features of intermediate complexity and their use in classification , 2002, Nature Neuroscience.

[31]  S. Thorpe,et al.  Taking the MAX from neuronal responses , 2003, Trends in Cognitive Sciences.

[32]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[33]  S. Treue.  Visual attention: the where, what, how and why of saliency , 2003, Current Opinion in Neurobiology.

[34]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[35]  Tomaso Poggio,et al.  Generalization in vision and motor control , 2004, Nature.

[36]  Rufin van Rullen,et al.  Neurons Tune to the Earliest Spikes Through STDP , 2005, Neural Computation.

[37]  Thomas Serre,et al.  Object recognition with features inspired by visual cortex , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[39]  Keiji Tanaka,et al.  Differences in onset latency of macaque inferotemporal neural responses to primate and non-primate faces. , 2005, Journal of neurophysiology.

[40]  Tomaso Poggio,et al.  Fast Readout of Object Identity from Macaque Inferior Temporal Cortex , 2005, Science.

[41]  Robert Desimone,et al.  Parallel and Serial Neural Mechanisms for Visual Search in Macaque Area V4 , 2005, Science.

[42]  Thomas Serre,et al.  A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex , 2005 .

[43]  David L. Sheinberg,et al.  Spike Count Reliability and the Poisson Hypothesis , 2006, The Journal of Neuroscience.

[44]  Gustavo Deco,et al.  Learning to Attend: Modeling the Shaping of Selectivity in Infero-temporal Cortex in a Categorization Task , 2006, Biological Cybernetics.

[45]  Adam Kepecs,et al.  Seeing at a glance, smelling in a whiff: rapid forms of perceptual decision making , 2006, Nature Reviews Neuroscience.

[46]  Simon J. Thorpe,et al.  Ultra-rapid object detection with saccadic eye movements: Visual processing speed revisited , 2006, Vision Research.

[47]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .