Abstract: Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency — as though these inferences are a reflex response of their cognitive apparatus. Furthermore, these inferences are drawn with reference to a large body of background knowledge. This remarkable human ability seems paradoxical given the results about the complexity of reasoning reported by researchers in artificial intelligence. It also poses a challenge for cognitive science and computational neuroscience: How can a system of simple and slow neuron-like elements represent a large body of systematic knowledge and perform a range of inferences with such speed? We describe a computational model that is a step toward addressing the cognitive science challenge and resolving the artificial intelligence paradox. We show how a connectionist network can encode millions of facts and rules involving n-ary predicates and variables, and perform a class of inferences in a few hundred msec. Efficient reasoning requires the rapid representation and propagation of dynamic bindings. Our model achieves this by i) representing dynamic bindings as the synchronous firing of appropriate nodes, ii) rules as interconnection patterns

Search for conjunctions of highly discriminable features can be rapid or even parallel. This article explores, three possible accounts based on (a) perceptual segregation, (b) conjunction detectors, and (c) inhibition controlled separately by two or more distractor features. Search rates for conjunctions of color, size, orientation, and direction of motion correlated closely with an independent measure of perceptual segregation. However, they appeared unrelated to the physi-ology of single-unit responses. Each dimension contributed additively to conjunction search rates, suggesting that each was checked independently of the others. Unknown targets appear to be found only by serial search for each in turn. Searching through 4 sets of distractors was slower than searching through 2. The results suggest a modification of feature integration theory, in which attention is controlled not only by a unitary "window " but also by a form of feature-based inhibition. Objects in the real world vary in a large number of prop-erties, at least some of which appear to be coded by special-ized, independent channels or modules in the perceptual

This paper describes how agents can learn an internal model of the world structurally by focusing on the problem of behavior-based articulation. We develop an on-line learning scheme -- the so-called mixture of recurrent neural net (RNN) experts -- in which a set of RNN modules becomes self-organized as experts on multiple levels in order to account for the different categories of sensory-motor flow which the robot experiences. Autonomous switching of activated modules in the lower level actually represents the articulation of the sensory-motor flow. In the meanwhile, a set of RNNs in the higher level competes to learn the sequences of module switching in the lower level, by which articulation at a further more abstract level can be achieved. The proposed scheme was examined through simulation experiments involving the navigation learning problem. Our dynamical systems analysis clarified the mechanism of the articulation; the possible correspondence between the articulation...

We study image segmentation on the basis of locally excitatory globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a potential for each oscillator so that only those oscillators with strong connections from their neighborhood can develop high potentials. Based on the concept of potential, a solution to remove noisy regions in an image is proposed for LEGION, so that it suppresses the oscillators corresponding to noisy regions, without affecting those corresponding to major regions. We show analytically that the resulting oscillator network separates an image into several major regions, plus a background consisting of all noisy regions, and illustrate network properties by computer simulation. The network exhibits a natural capacity in segmenting images. The oscillatory dynamics leads to a computer algorithm, which is applied successfully to segmenting real graylevel images. A number of issues regarding biological plausibility and perceptual organization are discussed. We argue that LEGION provides a novel and effective framework for image segmentation and figure-ground segregation. DeLiang Wang and David Terman Image Segmentation 1.

We are capable of drawing a variety of inferences effortlessly, spontaneously, and with remarkable efficiency — as though these inferences are a reflex response of our cognitive apparatus. This remarkable human ability poses a challenge for cognitive science and computational neuroscience: How can a network of slow neuron-like elements represent a large body of systematic knowledge and perform a wide range of inferences with such speed? The connectionist model Shruti attempts to address this challenge by demonstrating how a neurally plausible network can encode a large body of semantic and episodic facts, systematic rules, and knowledge about entities and types, and yet perform a wide range of explanatory and predictive inferences within a few hundred milliseconds. Relational structures (frames, schemas) are represented in Shruti by clusters of cells, and inference in Shruti corresponds to a transient propagation of rhythmic activity over such cell-clusters wherein dynamic bindings are represented by the synchronous firing of appropriate cells. Shruti encodes mappings across relational structures using high-efficacy links that enable the propagation of rhythmic activity, and it encodes items in long-term memory as coincidence and conincidence-error detector circuits that become active in response to the occurrence (or non-occurrence) of appropriate coincidences in the on going flux of rhythmic activity.

To study the mechanisms underlying covert orienting of attention in visual space, subjects were given advance cues indicating the probable locations of targets that they had to discriminate and localize. Direct peripheral cues (brightening of one of four boxes in peripheral vision) and symbolic central cues (an arrow at the fixation point indicating a probable peripheral box) were compared. Peripheral and central cues are believed to activate different reflexive and voluntary modes of orienting (Jonides, 1981; Posner, 1980). Experiment 1 showed that the time courses of facilitation and inhibition from peripheral and central cues were characteristic and different. Experiment 2 showed that voluntary orienting in response to symbolic central cues is interrupted by reflexive orienting to random peripheral flashes. Experiment 3 showed that irrelevant peripheral flashes also compete with relevant peripheral cues. The amount of interference varied systematically with the interval between the onset of the relevant cue and of the distracting flash (cue-flash onset asynchrony) and with the cuing condition. Taken together, these effects support a model for spatial attention with distinct but interacting reflexive and voluntary orienting mechanisms.

Abstract not found

We show that complex visual tasks, such as position and size invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a co-evolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons are evolved while freely interacting with their environments. We describe the application of this methodology in three sets of experiments, namely shape discrimination, car driving, and robot navigation. We show that these systems develop sensitivity to a number of oriented, retinotopic, visual features oriented edges, corners, height – and a behavioral repertoire to locate, bring, and keep these features in sensitive regions of the vision system, resembling strategies observed in simple insects.

Natural time-varying images possess significant temporal correlations when sampled frame by frame by the photoreceptors. These correlations persist even after retinal processing and hence, under natural activation conditions, the signal sent to the lateral geniculate nucleus is temporally redundant or inefficient. We explore the hypothesis that the LGN is concerned, among other things, with improving efficiency of visual representation through active temporal decorrelation of the retinal signal much in the same way that the retina improves efficiency by spatially decorrelating incoming images. Using some recently measured statistical properties of time-varying images, we predict the spatio-temporal receptive fields that achieve this decorrelation. It is shown that, because of neuronal nonlinearities, temporal decorrelation requires two response types, the lagged and nonlagged, just as spatial decorrelation requires on and off response types. The tuning and response properties of the p...

Researchers have long argued that an attentional mechanism is required to perform many vision tasks. This thesis includes an implementation and evaluation of an attentional prototype as it applies to early and intermediate levels of visual computation. The model is composed of a processing hierarchy and an attention beam that traverses the hierarchy, passing through the regions of greatest interest and inhibiting the regions that are not relevant. The amount of computation required is crucial to the derivation of this model. As a result, this scheme "scales up" extremely well with the size of the problem and in fact scales to human-size problems. In addition, the domain of input to the prototype is not limited to visual stimuli, making this system applicable to many different sensory modalities. Dimensions of attention such as localizing spatial regions of interset and ordering their importance are addressed, whereas other aspects of attention such as the role of task guidance are not....