Spatio–Temporal Adaptation in the Unsupervised Development of Networked Visual Neurons

There have been many computational models mimicking the visual cortex that are based on spatial adaptations of unsupervised neural networks. In this paper, we present a new model called neuronal cluster which includes spatial as well as temporal weights in its unified adaptation scheme. The ldquoin-placerdquo nature of the model is based on two biologically plausible learning rules, Hebbian rule and lateral inhibition. We present the mathematical demonstration that the temporal weights are derived from the delay in lateral inhibition. By training with the natural videos, this model can develop spatio-temporal features such as orientation selective cells, motion sensitive cells, and spatio-temporal complex cells. The unified nature of the adaption scheme allows us to construct a multilayered and task-independent attention selection network which uses the same learning rule for edge, motion, and color detection, and we can use this network to engage in attention selection in both static and dynamic scenes.

[1]  Aapo Hyvärinen,et al.  Topographic Independent Component Analysis , 2001, Neural Computation.

[2]  G L Gerstein,et al.  Spatiotemporal organization of cat lateral geniculate receptive fields. , 1976, Journal of neurophysiology.

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

[4]  H. K. HAltTLIn THE RESPONSE OF SINGLE OPTIC NERVE FIBERS OF THE VERTEBRATE EYE TO ILLUMINATION OF THE RETINA , 2004 .

[5]  Juha Karhunen,et al.  Locally linear independent component analysis , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[6]  Huicheng Zheng,et al.  Fast-Learning Adaptive-Subspace Self-Organizing Map: An Application to Saliency-Based Invariant Image Feature Construction , 2008, IEEE Transactions on Neural Networks.

[7]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[8]  J. Movshon,et al.  Spatial summation in the receptive fields of simple cells in the cat's striate cortex. , 1978, The Journal of physiology.

[9]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[10]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[11]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[12]  S Marcelja,et al.  Mathematical description of the responses of simple cortical cells. , 1980, Journal of the Optical Society of America.

[13]  Erkki Oja,et al.  A "nonnegative PCA" algorithm for independent component analysis , 2004, IEEE Transactions on Neural Networks.

[14]  Robert B. Fisher,et al.  Object-based visual attention for computer vision , 2003, Artif. Intell..

[15]  P. Foldiak,et al.  Adaptive network for optimal linear feature extraction , 1989, International 1989 Joint Conference on Neural Networks.

[16]  C. Koch,et al.  From stimulus encoding to feature extraction in weakly electric fish , 1996, Nature.

[17]  S. Yantis,et al.  Visual attention: control, representation, and time course. , 1997, Annual review of psychology.

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

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

[20]  Zhi-Hong Mao,et al.  Dynamics of Winner-Take-All Competition in Recurrent Neural Networks With Lateral Inhibition , 2007, IEEE Transactions on Neural Networks.

[21]  E. Oja Simplified neuron model as a principal component analyzer , 1982, Journal of mathematical biology.

[22]  D. Heeger Modeling simple-cell direction selectivity with normalized, half-squared, linear operators. , 1993, Journal of neurophysiology.

[23]  Y. Wang,et al.  Simulations of receptive-field dynamics , 1996, Trends in Neurosciences.

[24]  H. K. Hartline,et al.  INHIBITION IN THE EYE OF LIMULUS , 1956, The Journal of general physiology.

[25]  Simone Frintrop,et al.  VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search , 2006, Lecture Notes in Computer Science.

[26]  J. Daugman Two-dimensional spectral analysis of cortical receptive field profiles , 1980, Vision Research.

[27]  Juyang Weng,et al.  2008 Special issue , 2008 .

[28]  Christoph Rasche,et al.  Neuromorphic Excitable Maps for Visual Processing , 2007, IEEE Transactions on Neural Networks.

[29]  C. Enroth-Cugell,et al.  Algebraic Summation of Centre and Surround Inputs to Retinal Ganglion Cells of the Cat , 1970, Nature.

[30]  Juyang Weng,et al.  Where-what network 1: “Where” and “what” assist each other through top-down connections , 2008, 2008 7th IEEE International Conference on Development and Learning.

[31]  M. Sur,et al.  Visual behaviour mediated by retinal projections directed to the auditory pathway , 2000, Nature.

[32]  T. Yamada Control of tissue specificity: the pattern of cellular synthetic activities in tissue transformation. , 1966, American zoologist.

[33]  Peter Tino,et al.  IEEE Transactions on Neural Networks , 2009 .

[34]  C. Koch,et al.  A saliency-based search mechanism for overt and covert shifts of visual attention , 2000, Vision Research.

[35]  A Treisman,et al.  Feature analysis in early vision: evidence from search asymmetries. , 1988, Psychological review.

[36]  Zhaoping Li,et al.  A Neural Model of Contour Integration in the Primary Visual Cortex , 1998, Neural Computation.

[37]  I. Ohzawa,et al.  Receptive-field dynamics in the central visual pathways , 1995, Trends in Neurosciences.

[38]  Juyang Weng,et al.  Optimal In-Place Learning and the Lobe Component Analysis , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[39]  P. Z. Marmarelis,et al.  Analysis of Physiological Systems: The White-Noise Approach , 2011 .

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

[41]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[42]  L. Itti Quantitative modelling of perceptual salience at human eye position , 2006 .

[43]  Ralph Linsker,et al.  A Local Learning Rule That Enables Information Maximization for Arbitrary Input Distributions , 1997, Neural Computation.

[44]  J. Theeuwes Top-down search strategies cannot override attentional capture , 2004, Psychonomic bulletin & review.

[45]  Wang Yunjiu,et al.  EXTENDED GABOR FUNCTION MODEL AND SIMULATION OF SOME CHARACTERISTIC CURVES OF RECEPTIVE FIELD , 1988 .

[46]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[47]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[48]  Michael S. Falconbridge,et al.  A Simple Hebbian/Anti-Hebbian Network Learns the Sparse, Independent Components of Natural Images , 2006, Neural Computation.

[49]  D. Ruderman,et al.  Independent component analysis of natural image sequences yields spatio-temporal filters similar to simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

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

[51]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

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

[53]  Liqing Zhang,et al.  A Hierarchical Generative Model for Overcomplete Topographic Representations in Natural Images , 2007, 2007 International Joint Conference on Neural Networks.

[54]  G. F. Cooper,et al.  Development of the Brain depends on the Visual Environment , 1970, Nature.

[55]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[56]  Terence D. Sanger,et al.  Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.