PSYCHOLOGICAL SCIENCE Research Article UNSUPERVISED STATISTICAL LEARNING OF HIGHER-ORDER SPATIAL STRUCTURES FROM VISUAL SCENES

Three experiments investigated the ability of human observers to extract the joint and conditional probabilities of shape cooccurrences during passive viewing of complex visual scenes. Results indicated that statistical learning of shape conjunctions was both rapid and automatic, as subjects were not instructed to attend to any particular features of the displays. Moreover, in addition to single-shape frequency, subjects acquired in parallel several different higher-order aspects of the statistical structure of the displays, including absolute shape-position relations in an array, shape-pair arrangements independent of position, and conditional probabilities of shape co-occurrences. Unsupervised learning of these higher-order statistics provides support for Barlow's theory of visual recognition, which posits that detecting “suspicious coincidences” of elements during recognition is a necessary prerequisite for efficient learning of new visual features.

[1]  Hermann von Helmholtz,et al.  Treatise on Physiological Optics , 1962 .

[2]  I. G. Priest.  The Optical Society of America , 1962, Nature.

[3]  E. Gibson.  Principles of Perceptual Learning and Development , 1969 .

[4]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  E. Gibson,et al.  Principles of Perceptual Learning and Development , 1973 .

[6]  J. Hochberg.  On cognition in perception: Perceptual coupling and unconscious inference , 1981, Cognition.

[7]  L Hasher,et al.  Automatic processing of fundamental information: the case of frequency of occurrence. , 1984, The American psychologist.

[8]  H. B. Barlow,et al.  Finding Minimum Entropy Codes , 1989, Neural Computation.

[9]  M. Peterson,et al.  Frequency judgements: the problem of defining a perceptual event. , 1989, Journal of experimental psychology. Learning, memory, and cognition.

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

[11]  H. Pashler,et al.  Improvement in line orientation discrimination is retinally local but dependent on cognitive set , 1992, Perception & psychophysics.

[12]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

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

[14]  S. Hochstein,et al.  Attentional control of early perceptual learning. , 1993, Proceedings of the National Academy of Sciences of the United States of America.

[15]  A. Karni,et al.  The time course of learning a visual skill , 1993, Nature.

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

[17]  Geoffrey E. Hinton,et al.  The Helmholtz Machine , 1995, Neural Computation.

[18]  C. Malsburg.  Binding in models of perception and brain function , 1995, Current Opinion in Neurobiology.

[19]  R N Aslin,et al.  Statistical Learning by 8-Month-Old Infants , 1996, Science.

[20]  Penio S. Penev,et al.  Local feature analysis: A general statistical theory for object representation , 1996 .

[21]  Keiji Tanaka,et al.  Inferotemporal cortex and object vision. , 1996, Annual review of neuroscience.

[22]  M. Goldsmith,et al.  Statistical Learning by 8-Month-Old Infants , 1996 .

[23]  E. Newport,et al.  WORD SEGMENTATION : THE ROLE OF DISTRIBUTIONAL CUES , 1996 .

[24]  Bartlett W. Mel.  SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition , 1997, Neural Computation.

[25]  Geoffrey E. Hinton,et al.  Generative models for discovering sparse distributed representations. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[26]  D H Brainard,et al.  The Psychophysics Toolbox. , 1997, Spatial vision.

[27]  M. Tarr,et al.  Becoming a “Greeble” Expert: Exploring Mechanisms for Face Recognition , 1997, Vision Research.

[28]  S. Hochstein,et al.  Task difficulty and the specificity of perceptual learning , 1997, Nature.

[29]  D G Pelli,et al.  The VideoToolbox software for visual psychophysics: transforming numbers into movies. , 1997, Spatial vision.

[30]  E. Newport,et al.  Computation of Conditional Probability Statistics by 8-Month-Old Infants , 1998 .

[31]  M. Chun,et al.  Contextual Cueing: Implicit Learning and Memory of Visual Context Guides Spatial Attention , 1998, Cognitive Psychology.

[32]  Elizabeth K. Johnson,et al.  Statistical learning of tone sequences by human infants and adults , 1999, Cognition.

[33]  M. Chun,et al.  Top-Down Attentional Guidance Based on Implicit Learning of Visual Covariation , 1999 .

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

[35]  Terrence J. Sejnowski,et al.  Unsupervised Learning , 2018, Encyclopedia of GIS.

[36]  P. Quinn,et al.  Identification of Gender in Domestic-Cat Faces with and without Training: Perceptual Learning of a Natural Categorization Task , 1999, Perception.

[37]  J L Gallant,et al.  Sparse coding and decorrelation in primary visual cortex during natural vision. , 2000, Science.

[38]  Daphna Weinshall,et al.  Mechanisms of generalization in perceptual learning , 1998, Vision Research.

[39]  Bartlett W. Mel,et al.  Minimizing Binding Errors Using Learned Conjunctive Features , 2000, Neural Computation.

[40]  M. Hauser,et al.  Segmentation of the speech stream in a non-human primate: statistical learning in cotton-top tamarins , 2001, Cognition.

[41]  Erkki Oja,et al.  Unsupervised learning in neural computation , 2002, Theor. Comput. Sci..

[42]  K. Clark.  CONDITIONS FOR VERSATILE LEARNING , HELMHOLTZ ’ S UNCONSCIOUS INFERENCE , AND THE TASK OF PERCEPTION , 2002 .

[43]  M. Tarr,et al.  Visual Object Recognition , 1996, ISTCS.