A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training patterns. As a result of the competition, different networks learn different training patterns and, thus, learn to compute different functions. The architecture performs task decomposition in the sense that it learns to partition a task into two or more functionally independent vii tasks and allocates distinct networks to learn each task. In addition, the architecture tends to allocate to each task the network whose topology is most appropriate to that task, and tends to allocate the same network to similar tasks and distinct networks to dissimilar tasks. Furthermore, it can be easily modified so as to...

In this paper we propose a theoretical framework of distributed representations and a methodology of representational analysis for the study of distributed cognitive tasksÑtasks that require the processing of information distributed across the internal mind and the external environment. The basic principle of distributed representations is that the representational system of a distributed cognitive task is a set of internal and external representations, which together represent the abstract structure of the task. The basic strategy of representational analysis is to decompose the representation of a hierarchical task into its component levels so that the representational properties at each level can be independently examined. The theoretical framework and the methodology are used to analyze the hierarchical structure of the Tower of Hanoi problem. Based on this analysis, four experiments are designed to examine the representational properties of the Tower of Hanoi. Finally, the nature of external representations is discussed.

Introduction Marr (1982) may have been one of the first vision researchers to insist that in modeling vision it is important to separate the location of visual features from their type. He argued that in early stages of visual processing there must be "place tokens" that enable subsequent stages of the visual system to treat locations independent of what specific feature type was at that location. Thus, in certain respects a collinear array of diverse features could still be perceived as a line, and under certain conditions could function as such in perceptual phenomena like the Poggendorf illusion. The idea that locations and feature-types are encoded independently is not a new one. A closely related distinction was widely acknowledged in the literature on list-learning and letterrecognition, where it has long been known that item information could be encoded or retained independent of order information (e.g., Estes, Allmeyer & Reder, 1976; Co

The processes whereby our brains continue to learn about a changing world in a stable fashion throughout life are proposed to lead to conscious experiences. These processes include the learning of top-down expectations, the matching of these expectations against bottom-up data, the focusing of attention upon the expected clusters of information, and the development of resonant states between bottom-up and top-down processes as they reach an attentive consensus between what is expected and what is there in the outside world. It is suggested that all conscious states in the brain are resonant states, and that these resonant states trigger learning of sensory and cognitive representations. The models which summarize these concepts are therefore called Adaptive Resonance Theory, or ART, models. Psychophysical and neurobiological data in support of ART are presented from early vision, visual object recognition, auditory streaming, variable-rate speech perception, somatosensory perception, a...

Many researchers interested in connectionist models accept that such models are "neurally inspired " but do not worry too much about whether their models are biologically realistic. While such a position may be perfectly justifiable, the present paper attempts to illustrate how biological information can be used to constrain connectionist models. Two particular areas are discussed. The first section deals with visual information processing in the primate and human visual system. It is argued that speed with which visual information is processed imposes major constraints on the architecture and operation of the visual system. In particular, it seems that a great deal of processing must depend on a single bottum-up pass. The second section deals with biological aspects of learning algorithms. It is argued that although there is good evidence for certain coactivation related synaptic modification schemes, other learning mechanisms, including back-propagation, are not currently supported by experimental data.

... This article presents one alternative to the computer metaphor suggesting that brains are organized into independent modules. Evidence is reviewed that brains are organized into parallel processing streams with complementary properties. Hierarchical interactions within each stream and parallel interactions between streams create coherent behavioral representations that overcome the complementary deficiencies of each stream and support unitary conscious experiences. This perspective suggests how brain design reflects the organization of the physical world with which brains interact. Examples from perception, learning, cognition, and action are described, and theoretical concepts and mechanisms by which complementarity is accomplished are presented.

Abstract--The recognition of three-dimensional ( 3-D) objects from sequences of their two-dimensional ( 2-D) views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-1) view categories whose outputs are combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes us multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may be used for scene understanding by using a preprocessor and classifier that can determine both what objects are in a scene and where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaassian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the

This article develops the FACADE theory of 3-dimensional (3-D) vision and figure-ground separation to explain data concerning how 2-dimensional pictures give rise to 3-D percepts of occluding and occluded objects. The model describes how geometrical and contrastive properties of a picture can either cooperate or compete when fonning the boundaries and surface representations that subserve conscious percepts. Spatially long-range cooperation and spatially short-range competition work together to separate the boundaries of occluding figures from their occluded neighbors. This boundary ownership process is sensitive to image T junctions at which occluded figures contact occluding figures. These boundaries control the filling-in of color within multiple depth-sensitive surface representations. Feedback between surface and boundary representations strengthens consistent boundaries while inhibiting inconsistent ones. Both the boundary and the surface representations of occluded objects may be amodally completed, while the surface representations of unoccluded objects become visible through modal completion. Functional roles for conscious modal and amodal representations in object recognition, spatial attention, and reaching behaviors are discussed. Model interactions are interpreted in tenns of visual, temporal, and parietal cortices. The human urge to represent the three-dimensional (3-D)

CENTER FOR ADAPTNE SYSTEMS AND DEPARTMENT OF COGNITIVE AND NEURAL

How does the visual system learn an internal model of the external environment? How is this internal model used during visual perception? How are occlusions and background clutter so effortlessly discounted for when recognizing a familiar object? How is a particular object of interest attended to and recognized in the presence of other objects in the field of view? In this paper, we attempt to address these questions from the perspective of Bayesian optimal estimation theory. Using the concept of generative models and the statistical theory of Kalman filtering, we show how static and dynamic events occurring in the visual environment may be learned and recognized given only the input images. We also describe an extension of the Kalman filter model that can handle multiple objects in the field of view. The resulting robust Kalman filter model demonstrates how certain forms of attention can be viewed as an emergent property of the interaction between top–down expectations and bottom–up signals. Experimental results are provided to help demonstrate the ability of such a model to perform robust segmentation and recognition of objects and image sequences in the presence of occlusions and clutter.