Encoding Shape and Spatial Relations: The Role of Receptive Field Size in Coordinating Complementary Representations

An effective functional architecture facilitates interactions among subsystems that are often used together. Computer simulations showed that differences in receptive field sizes con promote such organization. When input was filtered through relatively small nonoverlapping receptive fields, artificial neural networks learned to categorize shapes relatively quickly: in contrast, when input wets filtered through relatively large overlapping receptive fields, networks learned to encode specific shape exemplars or metric spatial relations relatively quickly. Moreover, when the receptive field sizes were allowed to adapt during learning, networks developed smaller receptive fields when they were trained to categorize shapes or spatial relations, and developed larger receptive fields when they were trained to encode specific exemplars or metric distances. In addition, when pairs of networks were constrained to use input from the same type of receptive fields, networks learned a task faster when they were paired with networks that were trained to perform a compatible type of task. Finally, using a novel modular architecture, networks were not preassigned a task, but rather competed to perform the different tasks. Networks with small nonoverlapping receptive fields tended to win the competition for categorical tasks whereas networks with large overlapping receptive fields tended to win the competition for exemplar/metric tasks.

[1]  F. Kitterle,et al.  Hemispheric asymmetry in the processing of absolute versus relative spatial frequency , 1991, Brain and Cognition.

[2]  D. Lindsley Physiological psychology. , 1956, Annual review of psychology.

[3]  M. Dennis,et al.  Language acquisition following hemidecortication: Linguistic superiority of the left over the right hemisphere , 1976, Brain and Language.

[4]  Michael I. Jordan,et al.  Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks , 1990, Cogn. Sci..

[5]  J. E. Glynn,et al.  Numerical Recipes: The Art of Scientific Computing , 1989 .

[6]  Michael I. Jordan,et al.  A Competitive Modular Connectionist Architecture , 1990, NIPS.

[7]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[8]  William H. Press,et al.  Numerical Recipes: The Art of Scientific Computing , 1987 .

[9]  Steven J. Nowlan,et al.  Maximum Likelihood Competitive Learning , 1989, NIPS.

[10]  C. J. Marsolek Abstract visual-form representations in the left cerebral hemisphere. , 1995, Journal of experimental psychology. Human perception and performance.

[11]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[12]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[13]  Michael I. Jordan,et al.  Hierarchies of Adaptive Experts , 1991, NIPS.

[14]  S. Kosslyn,et al.  Wet Mind: The New Cognitive Neuroscience , 1995 .

[15]  Geoffrey E. Hinton,et al.  Evaluation of Adaptive Mixtures of Competing Experts , 1990, NIPS.

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

[17]  M. V. Kleeck Hemispheric differences in global versus local processing of hierarchical visual stimuli by normal subjects: New data and a meta-analysis of previous studies , 1989, Neuropsychologia.

[18]  I. Biederman Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

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

[20]  Jonathan Baxter,et al.  Learning internal representations , 1995, COLT '95.

[21]  S. Kosslyn,et al.  Categorical versus coordinate spatial relations: computational analyses and computer simulations. , 1992, Journal of experimental psychology. Human perception and performance.

[22]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[23]  R. Knight,et al.  Normal global-local analysis in patients with dorsolateral frontal lobe lesions , 1991, Neuropsychologia.

[24]  M. Dennis,et al.  Comprehension of syntax in infantile hemiplegics after cerebral hemidecortication: Left-hemisphere superiority , 1975, Brain and Language.

[25]  Geoffrey E. Hinton,et al.  The Bootstrap Widrow-Hoff Rule as a Cluster-Formation Algorithm , 1990, Neural Computation.

[26]  Michael I. Jordan,et al.  Task Decomposition through Competition in A , 1990 .

[27]  S. Kosslyn,et al.  Form-specific visual priming in the right cerebral hemisphere. , 1992, Journal of experimental psychology. Learning, memory, and cognition.

[28]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[29]  Drew H. Abney,et al.  Journal of Experimental Psychology : Human Perception and Performance Influence of Musical Groove on Postural Sway , 2015 .

[30]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[31]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[32]  Geoffrey E. Hinton Shape Representation in Parallel Systems , 1981, IJCAI.

[33]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[34]  R. Weale Vision. A Computational Investigation Into the Human Representation and Processing of Visual Information. David Marr , 1983 .

[35]  L. Robertson,et al.  Neuropsychological contributions to theories of part/whole organization , 1991, Cognitive Psychology.

[36]  M H Van Kleeck,et al.  Hemispheric differences in global versus local processing of hierarchical visual stimuli by normal subjects: new data and a meta-analysis of previous studies. , 1989, Neuropsychologia.

[37]  F. Kitterle,et al.  Visual field effects in the discrimination of sine-wave gratings , 1991, Perception & psychophysics.