Abstract

This thesis describes a connectionist model which learns to perceive spatial events and relations in simple movies of 2-dimensional objects, so as to name the events and relations as a speaker of a particular natural language would. Thus, the model learns perceptually grounded semantics for natural language spatial terms. Natural languages differ -- sometimes dramatically -- in the ways in which they structure space. The aim here has been to have the model be able to perform this learning task for terms from any natural language, and to have learning take place in the absence of explicit negative evidence, in order to rule out ad hoc solutions and to approximate the conditions under which children learn. The central focus of this thesis is a...

Citations

3011	Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images - Geman, Geman - 1984
2304	Learning Internal Representations by Error Propagation - Rumelhart, Hinton, et al. - 1986
1530	Introduction to the Theory of Neural Computation - Hertz, Krogh, et al. - 1991
1313	Finding structure in time - Elman - 1990
1297	Neural networks and physical systems with emergent collective computational abilities - Hopfield - 1982
1273	Robot Vision - Horn - 1986
721	Organization of Behavior - Hebb - 1949
632	Approximation by superposition’s of a sigmoidal function - Cybenko
584	Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex - Hubel, Wiesel - 1962
576	Precis of the modularity of mind - Fodor - 1985
549	A logical calculus of the ideas immanent in nervous activity - McCulloch, Pitts - 1943
490	Neurons with graded response have collective computational properties like those of two-state neurons - Hopfield
453	Principles of categorization - Rosch - 1978
408	Semantics and Cognition - Jackendoff - 1983
364	A learning algorithm for Boltzmann Machines - Ackley, Hinton, et al. - 1985
299	Recursive distributed representations - Pollack - 1990
292	dangerous things: What categories reveal about the mind - Lakoff - 1987
290	Connectionist Learning Procedures - Hinton - 1990
257	Learnability and Cognition: The Acquisition of Argument Structure - Pinker - 1989
242	A network that learns to recognize threedimensional objects. Nature 343 - Poggio, Edelman - 1990
240	Markov random field texture models - Cross, Jain - 1983
228	Attractor dynamics and parallelism in a connectionist sequential machine - Jordan - 1986
219	Connectionist models and their properties - Feldman, Ballard
205	An Empirical Study of Learning Speed in Back-Propagation Networks - Fahlman - 1988
199	Language and perception - Miller, Johnson-Laird - 1976
197	Basic color terms: Their universality and evolution - Berlin, Kay - 1969
167	Dynamic binding in a neural network for shape recognition - Hummel, Biederman - 1992
167	Task decomposition through competition in a modular architecture: The what and where in vision tasks - Jacobs, Jordan, et al. - 1990
167	The Need for Biases in Learning Generalizations - Mitchell - 1990
154	Learning distributed representations of concepts - Hinton - 1986
136	Spatial Vision - DeValois, DeValois - 1990
120	Language and Spatial Cognition. An Interdisciplinary Study of the Prepositions in English - Herskovits - 1986
107	On the internal structure of perceptual and semantic categories - Rosch - 1973
86	Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters - Bridle - 1989
85	Organization in vision: essays on gestalt perception - Kanizsa - 1979
75	Language Universals and Linguistic Typology - Comrie - 1989
74	Discharge patterns and functional organization of mammalian retina - KUFFLER - 1953
73	and network design strategies - LeCun - 1989
71	Hopfield; Large automatic learning, rule extraction and generalization - Denker, Schwartz, et al. - 1987
69	The Principle of Contrast: A constraint on language acquisition - Clark - 1987
67	The Recurrent Cascade-Correlation Architecture - Fahlman - 1991
66	A focused back-propagation algorithm for temporal pattern recognition - Mozer - 1989
61	Foundations of Cognitive Grammar I: Theoretical Prerequisites - Langacker - 1987
60	A Connectionist Approach to Word Sense Disambiguation - Cottrell - 1989
55	Recursive Auto-Associative Memory: Devising Compositional Distributed Representations - Pollack - 1988
54	Miniature language acquisition: A touchstone for cognitive science - Feldman, Lakoff, et al. - 1990
52	Temporal Scene Analysis: Conceptual Description of Object Movements - Badler - 1975
47	Design of a Neural Network Character Recognizer for a Touch Terminal - Guyon, Albrecht, et al. - 1991
42	Cortical connections and parallel processing: Structure and function - Ballard - 1986
39	Neural Representation of Conceptual Knowledge - Feldman - 1986