Representation, similarity, and the chorus of prototypes

It is proposed to conceive of representation as an emergent phenomenon that is supervenient on patterns of activity of coarsely tuned and highly redundant feature detectors. The computational underpinnings of the outlined concept of representation are (1) the properties of collections of overlapping graded receptive fields, as in the biological perceptual systems that exhibit hyperacuity-level performance, and (2) the sufficiency of a set of proximal distances between stimulus representations for the recovery of the corresponding distal contrasts between stimuli, as in multidimensional scaling. The present preliminary study appears to indicate that this concept of representation is computationally viable, and is compatible with psychological and neurobiological data.

[1]  Ronen Basri,et al.  Recognition by Linear Combinations of Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  L. Thurstone,et al.  A low of comparative judgement , 1927 .

[3]  Shimon Edelman,et al.  On Learning to Recognize 3-D Objects from Examples , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  R A Altes,et al.  Ubiquity of hyperacuity. , 1989, The Journal of the Acoustical Society of America.

[5]  Satosi Watanabe,et al.  Pattern Recognition: Human and Mechanical , 1985 .

[6]  Shimon Edelman,et al.  Representation With Receptive Fields: Gearing Up For Recognition , 1994 .

[7]  D. Perrett,et al.  Visual neurones responsive to faces in the monkey temporal cortex , 2004, Experimental Brain Research.

[8]  H. Putnam.  Representation and Reality , 1993 .

[9]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Richard Granger,et al.  Short-Latency Single Unit Processing in Olfactory Cortex , 1991, Journal of Cognitive Neuroscience.

[11]  Daphna Weinshall,et al.  A self-organizing multiple-view representation of 3D objects , 2004, Biological Cybernetics.

[12]  L. Thurstone.  A law of comparative judgment. , 1994 .

[13]  T. Poggio,et al.  A computational theory of human stereo vision , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[14]  Lawrence W. Barsalou,et al.  The instability of graded structure: implications for the nature of concepts , 1987 .

[15]  L. Sirovich,et al.  Equivalence classes of visual stimuli , 1978, Vision Research.

[16]  A. Tversky,et al.  Foundations of multidimensional scaling. , 1968, Psychological review.

[17]  Shimon Edelman,et al.  Learning to Recognize Faces from Examples , 1992, ECCV.

[18]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[19]  Hilary Kornblith,et al.  Inductive Inference and Its Natural Ground: An Essay in Naturalistic Epistemology , 1993 .

[20]  G. Rhodes.  Looking at Faces: First-Order and Second-Order Features as Determinants of Facial Appearance , 1988, Perception.

[21]  D C Van Essen,et al.  Shifter circuits: a computational strategy for dynamic aspects of visual processing. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Tomaso Poggio,et al.  From Understanding Computation to Understanding Neural Circuitry , 1976 .

[23]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

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

[25]  A. Tversky.  Features of Similarity , 1977 .

[26]  W. Quine.  Ontological Relativity and Other Essays , 1969 .

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

[28]  John Cerella,et al.  Pigeons and perceptrons , 1986, Pattern Recognit..

[29]  Richard Granger,et al.  Higher olfactory processes: perceptual learning and memory , 1991, Current Opinion in Neurobiology.

[30]  R N Shepard,et al.  Multidimensional Scaling, Tree-Fitting, and Clustering , 1980, Science.

[31]  A. J. Mistlin,et al.  Visual neurones responsive to faces , 1987, Trends in Neurosciences.

[32]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[33]  T. Poggio,et al.  Networks and the best approximation property , 1990, Biological Cybernetics.

[34]  Y. Miyashita,et al.  Neural organization for the long-term memory of paired associates , 1991, Nature.

[35]  Joseph Margolis,et al.  The Truth About Relativism , 1991 .

[36]  S. Edelman,et al.  Generalization of object recognition in human vision across stimulus transformations and deformations , 1990 .

[37]  S. Harnad.  Categorical Perception: The Groundwork of Cognition , 1990 .

[38]  Lee R. Brooks.  Decentralized control of categorization: The role of prior processing episodes. , 1987 .

[39]  David Haussler,et al.  Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..

[40]  Keiji Tanaka.  Inferotemporal cortex and higher visual functions , 1992, Current Opinion in Neurobiology.

[41]  R. Desimone,et al.  Stimulus-selective properties of inferior temporal neurons in the macaque , 1984, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[42]  D. B. Bender,et al.  Visual properties of neurons in inferotemporal cortex of the Macaque. , 1972, Journal of neurophysiology.

[43]  M. Young,et al.  On oscillating neuronal responses in the visual cortex of the monkey. , 1992, Journal of neurophysiology.

[44]  T Poggio,et al.  Fast perceptual learning in visual hyperacuity. , 1991, Science.

[45]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[46]  S. Edelman.  Representation of Similarity in 3D Object Discrimination , 1995 .

[47]  R. Shepard,et al.  Toward a universal law of generalization for psychological science. , 1987, Science.

[48]  William Bialek,et al.  Reading a Neural Code , 1991, NIPS.

[49]  R. Nosofsky.  Tests of an exemplar model for relating perceptual classification and recognition memory. , 1991, Journal of experimental psychology. Human perception and performance.

[50]  O. G. Selfridge,et al.  Pandemonium: a paradigm for learning , 1988 .

[51]  D Marr,et al.  Early processing of visual information. , 1976, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[52]  Shimon Edelman,et al.  Models of Perceptual Learning in Vernier Hyperacuity , 1993, Neural Computation.

[53]  Stephen M. Omohundro,et al.  Efficient Algorithms with Neural Network Behavior , 1987, Complex Syst..

[54]  H. Spitzer,et al.  Increased attention enhances both behavioral and neuronal performance. , 1988, Science.

[55]  Herbert Feigl,et al.  The Mental and the Physical: The Essay and a Postscript , 1967 .

[56]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[57]  O. Braddick.  Visual hyperacuity. , 1984, Nature.

[58]  Willard Van Orman Quine,et al.  Word and Object , 1960 .

[59]  S. Edelman,et al.  Long-term learning in vernier acuity: Effects of stimulus orientation, range and of feedback , 1993, Vision Research.

[60]  R. Cummins.  Meaning and mental representation , 1990 .

[61]  Dana H. Ballard,et al.  Cortical connections and parallel processing: Structure and function , 1986, Behavioral and Brain Sciences.

[62]  Jan J. Koenderink,et al.  Discrimination thresholds for channel-coded systems , 1992, Biological Cybernetics.

[63]  R. Desimone,et al.  The representation of stimulus familiarity in anterior inferior temporal cortex. , 1993, Journal of neurophysiology.

[64]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[65]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[66]  Tomaso A. Poggio,et al.  Extensions of a Theory of Networks for Approximation and Learning , 1990, NIPS.

[67]  K. Tanaka.  Column structure of inferotemporal cortex: "visual alphabet" or "differential amplifiers"? , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[68]  T. Poggio.  A theory of how the brain might work. , 1990, Cold Spring Harbor symposia on quantitative biology.

[69]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[70]  M. Hasselmo,et al.  The effect of learning on the face selective responses of neurons in the cortex in the superior temporal sulcus of the monkey , 2004, Experimental Brain Research.

[71]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[72]  E. Brunswik.  Perception and the Representative Design of Psychological Experiments , 1957 .

[73]  Joanne L. Miller,et al.  Feature Detectors and Speech Perception: A Critical Evaluation , 1982 .

[74]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[75]  D. Medin,et al.  The role of theories in conceptual coherence. , 1985, Psychological review.

[76]  D. Tanné,et al.  Perceptual learning: learning to see , 1994, Current Opinion in Neurobiology.

[77]  S. Stich.  The Fragmentation Of Reason , 1990 .

[78]  E. Markman.  Categorization and naming in children , 1989 .

[79]  I. Biederman,et al.  Evidence for Complete Translational and Reflectional Invariance in Visual Object Priming , 1991, Perception.