Emergence of filters from natural scenes in a sparse spike coding scheme

Abstract As an alternative to classical representations in machine learning algorithms, we explore coding strategies using events as is observed for spiking neurons in the central nervous system. Focusing on visual processing, we have previously shown that we may define a sparse spike coding scheme by implementing accordingly lateral interactions (Neurocomputing 57 (2004) 125). This class of algorithms is both compatible with biological constraints and also to neurophysiological observations and yields a performant algorithm of computing by events. We explore here learning mechanisms to unsupervisely derive an optimal overcomplete set of filters based on previous work of (Vision Res. 37 (1998) 3311) and show its biological relevance.

[1]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[2]  Manuel Samuelides,et al.  Sparse image coding using an asynchronous spiking neural network , 2002, ESANN.

[3]  Simon J. Thorpe,et al.  Coding static natural images using spiking event times: do neurons Cooperate? , 2004, IEEE Transactions on Neural Networks.

[4]  Adrian edgar douglas.  The basis of sensation: the action of the sense organs. , 1964 .

[5]  Terrence J. Sejnowski,et al.  Learning Overcomplete Representations , 2000, Neural Computation.

[6]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[7]  D. Field,et al.  Natural image statistics and efficient coding. , 1996, Network.

[8]  E. Castet,et al.  Temporal dynamics of motion integration for the initiation of tracking eye movements at ultra-short latencies , 2000, Visual Neuroscience.

[9]  R. Linsker,et al.  From basic network principles to neural architecture , 1986 .

[10]  A. Hill.  The Basis of Sensation: the Action of the Sense Organs , 1929, Nature.

[11]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[12]  Bruno A. Olshausen,et al.  Learning sparse wavelet codes for natural images , 2000, SPIE Optics + Photonics.

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

[14]  J. H. Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998 .

[15]  Simon J. Thorpe,et al.  Sparse spike coding in an asynchronous feed-forward multi-layer neural network using matching pursuit , 2004, Neurocomputing.

[16]  J. V. van Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[17]  Bernd Fritzke,et al.  Unsupervised ontogenic networks , 1997 .

[18]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[19]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.

[20]  R Linsker,et al.  From basic network principles to neural architecture: emergence of orientation-selective cells. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[21]  Manuel Samuelides,et al.  Coherence detection in a spiking neuron via Hebbian learning , 2002, Neurocomputing.

[22]  Charles Poynton.  Frequently Asked Questions about Gamma , 1998 .

[23]  Pierre Comon.  Independent component analysis - a new concept? signal processing , 1994 .

[24]  John Daugman,et al.  Gabor wavelets for statistical pattern recognition , 1998 .

[25]  S. Thorpe,et al.  Speed of processing in the human visual system , 1996, Nature.