Processing visual stimuli using hierarchical spiking neural networks

Based on spiking neuron models and different receptive field models, hierarchical networks are proposed to process visual stimuli, in which multiple overlapped objects are represented by different orientation bars. The main purpose of this paper is to show that hierarchical spiking neural networks are able to segment the objects and bind their pixels to form shapes of objects using local excitatory lateral connections. The presented architecture is based on biologically inspired hierarchical structures. Segmentation is achieved through temporal correlation of neuron activities. The properties of these networks are demonstrated using a series of visual scenes representing different stimuli settings.

[1]  DeLiang Wang,et al.  A dynamically coupled neural oscillator network for image segmentation , 2002, Neural Networks.

[2]  Christof Koch,et al.  Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series) , 1998 .

[3]  Joachim M. Buhmann,et al.  Sensory segmentation with coupled neural oscillators , 1992, Biological Cybernetics.

[4]  Vivien A. Casagrande,et al.  Biophysics of Computation: Information Processing in Single Neurons , 1999 .

[5]  Wulfram Gerstner,et al.  A neuronal learning rule for sub-millisecond temporal coding , 1996, Nature.

[6]  Qingxiang Wu,et al.  A Novel Approach for the Implementation of Large Scale Spiking Neural Networks on FPGA Hardware , 2005, IWANN.

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

[8]  S. J. Thorpe,et al.  Reverse engineering of the visual system using networks of spiking neurons , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[9]  T. Poggio,et al.  Neural mechanisms of object recognition , 2002, Current Opinion in Neurobiology.

[10]  C. Koch,et al.  Invariant visual representation by single neurons in the human brain , 2005, Nature.

[11]  M. Meister,et al.  Dynamic predictive coding by the retina , 2005, Nature.

[12]  Günther Palm,et al.  Scene segmentation by spike synchronization in reciprocally connected visual areas. II. Global assemblies and synchronization on larger space and time scales , 2002, Biological Cybernetics.

[13]  Wulfram Gerstner,et al.  Spiking Neuron Models: An Introduction , 2002 .

[14]  Risto Miikkulainen,et al.  Contour integration and segmentation with self-organized lateral connections , 2004, Biological Cybernetics.

[15]  E. Marder,et al.  Plasticity in single neuron and circuit computations , 2004, Nature.

[16]  Xuelong Li,et al.  General Tensor Discriminant Analysis and Gabor Features for Gait Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Risto Miikkulainen,et al.  Topographic Receptive Fields and Patterned Lateral Interaction in a Self-Organizing Model of the Primary Visual Cortex , 1997, Neural Computation.

[18]  A. Belatreche,et al.  Simulation of Intelligent Computational Models in Biological Systems , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[19]  K. Meier,et al.  RUPRECHT-KARLS-UNIVERSITÄT HEIDELBERG , 2002 .

[20]  H Sompolinsky,et al.  Global processing of visual stimuli in a neural network of coupled oscillators. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[21]  Joachim M. Buhmann,et al.  Image Segmentation by Networks of Spiking Neurons , 2005, Neural Computation.

[22]  Qingxiang Wu,et al.  Learning Mechanisms in Networks of Spiking Neurons , 2007, Trends in Neural Computation.

[23]  T. Gawne,et al.  Responses of primate visual cortical neurons to stimuli presented by flash, saccade, blink, and external darkening. , 2002, Journal of neurophysiology.

[24]  L. Abbott,et al.  Cortical Development and Remapping through Spike Timing-Dependent Plasticity , 2001, Neuron.

[25]  Qingxiang Wu,et al.  Adaptive Co-ordinate Transformation Based on a Spike Timing-Dependent Plasticity Learning Paradigm , 2005, ICNC.

[26]  Günther Palm,et al.  Scene segmentation by spike synchronization in reciprocally connected visual areas. I. Local effects of cortical feedback , 2002, Biological Cybernetics.

[27]  T. Gawne,et al.  Responses of primate visual cortical V4 neurons to simultaneously presented stimuli. , 2002, Journal of neurophysiology.

[28]  N. Swindale.  The development of topography in the visual cortex: a review of models. , 1996, Network.

[29]  Xuelong Li,et al.  Supervised Tensor Learning , 2005, ICDM.

[30]  Gopathy Purushothaman,et al.  Moving ahead through differential visual latency , 1998, Nature.

[31]  Peter Dayan,et al.  Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems , 2001 .

[32]  S. Thorpe,et al.  Surfing a spike wave down the ventral stream , 2002, Vision Research.

[33]  Risto Miikkulainen,et al.  Self-organization and segmentation in a laterally connected orientation map of spiking neurons , 1998, Neurocomputing.

[34]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[35]  George L. Gerstein,et al.  A neural network model for texture discrimination , 1993, Biological Cybernetics.

[36]  Roman Borisyuk,et al.  Oscillatory model of attention-guided object selection and novelty detection , 2004, Neural Networks.