Acquiring ontological categories through interaction

We present an experimental framework for the study of a computational agents acquisition of ontological categories through interaction with a human agent. This interaction takes the form of joint attention in a shared visual environment. Through a game of guessing words, the computational agent adapts its categorization system - a CALM-based neural architecture with a set of Gabor lters - and develops a shared lexicon with the human agent. This paper report initial experimental results.

[1]  Joseph J. Atick,et al.  What Does the Retina Know about Natural Scenes? , 1992, Neural Computation.

[2]  Jacob M.J. Murre,et al.  Learning and Categorization in Modular Neural Networks , 1992 .

[3]  I. T. Draper.  THE WORKING BRAIN (AN INTRODUCTION TO NEUROPSYCHOLOGY) , 1974 .

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

[5]  J. Eccles.  The modular operation of the cerebral neocortex considered as the material basis of mental events , 1981, Neuroscience.

[6]  I. Biederman,et al.  Surface versus edge-based determinants of visual recognition , 1988, Cognitive Psychology.

[7]  Tijsseling Ag,et al.  Connectionist models of catergorization : a dynamical approach to cognition. , 1998 .

[8]  J. S. Barlow.  The mindful brain: B.M. Edelman and V.B. Mountcastle (MIT Press, Cambridge, Mass., 1978, 100 p., U.S. $ 10.00) , 1979 .

[9]  V. Mountcastle,et al.  An organizing principle for cerebral function : the unit module and the distributed system , 1978 .

[10]  D. Hubel,et al.  Segregation of form, color, movement, and depth: anatomy, physiology, and perception. , 1988, Science.

[11]  T. Shallice,et al.  Isolating Cognitive Modules with the Dual-Task Paradigm: Are Speech Perception and Production Separate Processes? , 1985, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[12]  J. Szentágothai.  The ‘module-concept’ in cerebral cortex architecture , 1975, Brain Research.

[13]  Dare A. Baldwin,et al.  The Ontogeny of Social Information Gathering , 1996 .

[14]  G. V. Van Hoesen,et al.  Prosopagnosia , 1982, Neurology.

[15]  J.G. Daugman,et al.  Entropy reduction and decorrelation in visual coding by oriented neural receptive fields , 1989, IEEE Transactions on Biomedical Engineering.

[16]  S. Kosslyn,et al.  Components of high-level vision: A cognitive neuroscience analysis and accounts of neurological syndromes , 1990, Cognition.

[17]  Alice C. Harris,et al.  Historical Syntax in Cross-Linguistic Perspective , 1995 .

[18]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[19]  Christoph Palm,et al.  Gabor Filtering of Complex Hue/Saturation Images for Color Texture Classification , 2000 .

[20]  Angelo Cangelosi,et al.  From robotic toil to symbolic theft: Grounding transfer from entry-level to higher-level categories1 , 2000, Connect. Sci..

[21]  Ted Briscoe,et al.  Linguistic Evolution through Language Acquisition: Formal and Computational Models. , 2002 .