Integrating Subsymbolic and Symbolic Processing in Artificial Vision

We approach the integration between symbolic and subsymbolic processing within a hybrid model of visual perception, intended for an autonomous intelligent system. No hypotheses are made about the adequacy of this model as a model of human vision: the proposed model is currently under development for a robot system. We propose an associative mapping mechanism, that relates the constructs of the symbolic representation to a geometric representation of the observed scene. The symbolic representation is expressed in terms of a formalism provided with compositional structure. The geometric representation is obtained by making use of a geometric modelling system based on superquadrics. We describe a possible realization of the mapping mechanism by means of a feed-forward neural network architecture based on the backpropagation rule, presenting some results of a partial implementation.

[1]  Geoffrey E. Hinton,et al.  Deterministic Boltzmann Learning in Networks with Asymmetric Connectivity , 1991 .

[2]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[3]  Hector J. Levesque,et al.  An Essential Hybrid Reasoning System: Knowledge and Symbol Level Accounts of KRYPTON , 1985, IJCAI.

[4]  Wayne D. Gray,et al.  Basic objects in natural categories , 1976, Cognitive Psychology.

[5]  Edoardo Ardizzone,et al.  Geometric and conceptual knowledge representation within a generative model of visual perception , 1989, J. Intell. Robotic Syst..

[6]  S. Grossberg.  Neural Networks and Natural Intelligence , 1988 .

[7]  Richard W. Weyhrauch,et al.  Prolegomena to a Theory of Mechanized Formal Reasoning , 1980, Artif. Intell..

[8]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[9]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[10]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[11]  Barbara Hayes-Roth,et al.  A Blackboard Architecture for Control , 1985, Artif. Intell..

[12]  S. GAGLIO,et al.  VISUAL PERCEPTION: AN OUTLINE OF A GENERATIVE THEORY OF INFORMATION FLOW ORGANIZATION , 1984 .

[13]  Terrence J. Sejnowski,et al.  A Parallel Network that Learns to Play Backgammon , 1989, Artif. Intell..

[14]  Nigel Goddard,et al.  Rochester Connectionist Simulator , 1989 .

[15]  Jake K. Aggarwal,et al.  Identification of 3D objects from multiple silhouettes using quadtrees/octrees , 1985, Comput. Vis. Graph. Image Process..

[16]  Eleanor Rosch,et al.  Principles of Categorization , 1978 .

[17]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[18]  ARISTIDES A. G. REQUICHA,et al.  Representations for Rigid Solids: Theory, Methods, and Systems , 1980, CSUR.

[19]  D. Hofstadter,et al.  Godel, Escher, Bach: An Eternal Golden Braid , 1979 .

[20]  Ronald J. Brachman,et al.  An overview of the KL-ONE Knowledge Representation System , 1985 .

[21]  P. Johnson-Laird.  Mental models , 1989 .

[22]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[23]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[24]  Ronald J. Brachman,et al.  An Overview of the KL-ONE Knowledge Representation System , 1985, Cogn. Sci..

[25]  D. Whitteridge,et al.  Learning and Relearning , 1959, Science's STKE.

[26]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

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