Advanced perceptual systems are faced with the problem of securing a principled relationship between the world and its internal representation. I propose a unified approach to visual representation, based on Shepard's (1968) notion of second-order isomorphism. According to the proposed theory, a shape is represented internally by the responses of a few tuned modules, each of which is broadly selective for some reference shape, whose similarity to the stimulus it measures. The result is a philosophically appealing, computationally feasible, biologically credible, and formally veridical representation of a distal shape space. This approach supports representation of and discrimination among shapes radically different from the reference ones, while bypassing the need for the computationally problematic decomposition into parts; it also addresses the needs of shape categorization, and can be used to derive a range of models of perceived similarity. Representation is Representation of Sim...

Our current understanding of the primate cerebral cortex (neocortex) and in particular the posterior, sensory association cortex has matured to a point where it is possible to develop a family of graphical models that capture the structure, scale and power of the neocortex for purposes of associative recall, sequence prediction and pattern completion among other functions. Implementing such models using readily available computing clusters is now within the grasp of many labs and would provide scientists with the opportunity to experiment with both hard-wired connection schemes and structure-learning algorithms inspired by animal learning and developmental studies. While neural circuits involving structures external to the neocortex such as the thalamic nuclei are less well understood, the availability of a computational model on which to test hypotheses would likely accelerate our understanding of these circuits. Furthermore, the existence of an agreedupon cortical substrate would not only facilitate our understanding of the brain but enable researchers to combine lessons learned from biology with state-of-theart graphical-model and machine-learning techniques to design hybrid systems that combine the best of biological and traditional computing approaches.

The orbital frontal cortex appears to be involved in learning the rules of goal-directed behavior necessary to perform the correct actions based on perception to accomplish different tasks. The activity of orbitofrontal neurons changes dependent upon the specific task or goal involved, but the functional role of this activity in performance of specific tasks has not been fully determined. Here we present a model of prefrontal cortex function using networks of integrate-and-fire neurons arranged in minicolumns. This network model forms associations between representations of sensory input and motor actions, and uses these associations to guide goal-directed behavior. The selection of goal-directed actions involves convergence of the spread of activity from the goal representation with the spread of activity from the current state. This spiking network model provides a biological implementation of the action selection process used in reinforcement learning theory. The spiking activity shows properties similar to recordings of orbitofrontal neurons during task performance.

Pattern recognition systems that are invariant to shape, pose, lighting and texture are never sufficiently selective; they suffer a high rate of “false alarms”. How are biological vision systems both invariant and selective? Specifically, how are proper arrangements of sub-patterns distinguished from the chance arrangements that defeat selectivity in artificial systems? The answer may lie in the nonlinear dynamics that characterize complex and other invariant cell types: these cells are temporarily more receptive to some inputs than to others (functional connectivity). One consequence is that pairs of such cells with overlapping receptive fields will possess a related property that might be termed functional common input. Functional common input would induce high correlation exactly when there is a match in the sub-patterns appearing in the overlapping receptive fields. These correlations, possibly expressed as a partial and highly local synchrony, would preserve the selectivity otherwise lost to invariance.

Human-level visual performance has remained largely beyond the reach of engineered systems despite decades of research and significant advances in problem formulation, algorithms and computing power. We posit that significant progress can be made by combining existing technologies from machine vision, insights from theoretical neuroscience and large-scale distributed computing. Such claims have been made before and so it is quite reasonable to ask what are the new ideas we bring to the table that might make a difference this time around. From a theoretical standpoint, our primary point of departure from current practice is our reliance on exploiting time in order to turn an otherwise intractable unsupervised problem into a locally semi-supervised, and plausibly tractable, learning problem. From a pragmatic perspective, our system architecture follows what we know of cortical neuroanatomy and provides a solid foundation for scalable hierarchical inference. This combination of features provides the framework for implementing a wide range of robust object-recognition capabilities. In July of 2005, one of us (Dean) presented a paper at AAAI entitled “A Computational Model of the Cerebral Cortex ” (Dean 2005). The paper described a graphical model of the visual cortex inspired by David Mumford’s computational architecture (1991; 1992; 2003). At that same meeting, Jeff Hawkins gave an invited talk entitled “From

Neural network information is mainly conveyed through (i) event-based quanta, spikes, whereas highlevel representation of the related processing is almost always modeled in (ii) some continuous framework. Here, we propose a link between (i) and (ii), so that we can derive the spiking network parameters given interpretation of the related processing.

Information geometry is a method of analyzing the geometrical structure of a family of information systems. A family of neural networks forms a neuromanifold. It is important to study its geometrical structures for elucidating its capabilities of information processing. The present paper proposes a new mathematical theory of dynamic interactions of a lower and a higher neural systems by feedback and feedforward connections. Here, a new duality structure is introduced in the Bayesian framework from the point of view of information geometry. 1 Introduction Theoreticians have so far speculated some basic but primitive mechanisms of information processing in the brain. We can mention, among others, the autocorrelation associative memory model or the Boltzmann machine (its stochastic version), and the formation of topological maps by self-organization, and so on. However, it is believed that a fundamental role is played by a much more complex hierarchical structure: It is, for example, dy...

Visual processes do not amount to a simple filtering process performed by a series of hierarchical modules. They allow to select the items immediately useful for the current action from the information included in the external scene. To perform this selection, attentional top-down controls must combine with bottom-up information issued from the retina. In the prospect to understand how these informations are fused together, a computational model of the first steps of the visual process able to account for the pre-attentional and attentional mechanisms involved in visual search has been developed. This model, called Competitive Search, integrates the dynamical aspects of a local dynamical architecture. It accounts for 'pop-out' and attentional phenomena involved in the search for conjunctive targets without introducing ad hoc hypothetical mechanisms such as the attentional spotlight hypothesis. It suggests that such metaphors, issued from the conventional cognitive psychology, may in fa...

We present a system for the automatic interpretation of cluttered scenes containing multiple partly occluded objects in front of unknown, complex backgrounds. The system is based on an extended elastic graph matching algorithm that allows the explicit modeling of partial occlusions. Our approach extends an earlier system in two ways. First, we use elastic graph matching in stereo image pairs to increase matching robustness and disambiguate occlusion relations. Second, we use richer feature descriptions in the object models by integrating shape and texture with color features. We demonstrate that the combination of both extensions substantially increases recognition performance. The system learns about new objects in a simple one-shot learning approach. Despite the lack of statistical information in the object models and the lack of an explicit background model, our system performs surprisingly well for this very difficult task. Our results underscore the advantages of view-based feature constellation representations for difficult object recognition problems.

Abstract – The paper focuses on extracting and fusing visual feature information to discern targets much like a human fuses visual, auditory, and somatosensory data. Extraction of features is performed using a Pulse Coupled Neural Network to simulate visual-cortex processing of linking related-feature information. The feature-based biological sensor fusion approach extracts features from images, associates relevant features, and uses a belief filter to confirm or deny target identity.