Invariant encoding of spatial stimulus topology in the temporal domain

Abstract Invariant representations emerge as a central topic in vision research. Here we investigate a transformation of visual spatial patterns by an ensemble of laterally coupled neurons into the temporal domain. The central property of the network leading to this transformation is the monotonic relationship of transmission delays between neurons with increasing distance. We show that stimuli become encoded in the temporal population activity and that this representation is invariant with respect to translations, rotations and small distortions. Furthermore, the proposed model provides a rapid encoding in accordance with physiological results.

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

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

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

[4]  W. Bair.  Spike timing in the mammalian visual system , 1999, Current Opinion in Neurobiology.

[5]  M. Tovée,et al.  Information encoding and the responses of single neurons in the primate temporal visual cortex. , 1993, Journal of neurophysiology.

[6]  Jonathan D. Victor,et al.  Metric-space analysis of spike trains: theory, algorithms and application , 1998, q-bio/0309031.

[7]  Minami Ito,et al.  Columns for visual features of objects in monkey inferotemporal cortex , 1992, Nature.

[8]  Wolf Singer,et al.  Time as coding space? , 1999, Current Opinion in Neurobiology.

[9]  Edmund T. Rolls,et al.  Functions of the Primate Temporal Lobe Cortical Visual Areas in Invariant Visual Object and Face Recognition , 2000, Neuron.

[10]  Dean V. Buonomano,et al.  A Neural Network Model of Temporal Code Generation and Position-Invariant Pattern Recognition , 1999, Neural Computation.

[11]  R. Pfeifer,et al.  Connectionism in Perspective , 1989 .

[12]  B J Richmond,et al.  Temporal encoding of two-dimensional patterns by single units in primate inferior temporal cortex. II. Quantification of response waveform. , 1987, Journal of neurophysiology.

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

[14]  S. Thorpe,et al.  1 BIOLOGICAL CONSTRAINTS ON CONNECTIONIST MODELLING , 1989 .

[15]  Wilfried Brauer,et al.  Translation-invariant pattern recognition based on Synfire chains , 1999, Biological Cybernetics.

[16]  David I. Perrett,et al.  Neurophysiology of shape processing , 1993, Image Vis. Comput..

[17]  M. Tovée,et al.  Information encoding in short firing rate epochs by single neurons in the primate temporal visual cortex , 1995 .

[18]  Minami Ito,et al.  Size and position invariance of neuronal responses in monkey inferotemporal cortex. , 1995, Journal of neurophysiology.

[19]  Keiji Tanaka.  Mechanisms of visual object recognition: monkey and human studies , 1997, Current Opinion in Neurobiology.

[20]  R Van Rullen,et al.  Face processing using one spike per neurone. , 1998, Bio Systems.