When a visual image consists of a figure against a background, V1 cells are physiologically observed to give higher responses to image regions corresponding to the figure relative to their responses to the background. The medial axis of the figure also induces relatively higherresponses compared to responses to other locations in the figure (except for the boundary between the figure and the background). Since the receptive fields of V1 cells are very small comparedwith the global scale of the figure-ground and medial axis effects, it has been suggested that these effects may be caused by feedback from higher visual areas. I show how these effects can be accounted for by V1 mechanisms when the size of the figure is small or is of a certain scale. They are a manifestation of the processes of pre-attentive segmentation which detect and highlight the boundaries between homogeneous image regions. 1 Introduction Segmenting figure from ground is one of the most important visual tasks.

Stochastic fluctuations of voltage-gated ion channels generate current and voltage noise in neuronal membranes. This noise may be a critical determinantof the efficacy of information processing within neural systems. Using Monte-Carlo simulations, we carry out a systematic investigation ofthe relationship between channel kinetics and the resulting membrane voltage noise using a stochastic Markov version of the Mainen-Sejnowski model of dendritic excitability in cortical neurons. Our simulations show that kinetic parameters which lead to an increase in membrane excitability (increasing channel densities, decreasing temperature) alsolead to an increase in the magnitude of the sub-threshold voltage noise. Noise also increases as the membrane is depolarized from rest towards threshold. This suggests that channel fluctuations may interfere witha neuron's ability to function as an integrator of its synaptic inputs and may limit the reliability and precision of neural information processing.

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a predefined or incrementally learnedfeature space and is specifically tailored for learning in the presence of a very large number of features. A wide range of face images in different poses, with different expressions and under different lighting conditions are used as a training set to capture the variations of human faces. Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and others. Furthermore,learning and evaluation using the SNoW-based method are significantly more efficient than with other methods. 1 Introduction Growing interest in intelligent human computer interactions has motivated a recent surge in research on problems such as face tracking, pose estimation, face expression and gesture recognition. Most methods, however, assume human faces in their input images have been detected and localized.

We propose and analyze a class of actor-critic algorithms for simulation-based optimization of a Markov decision process over a parameterized family of randomized stationary policies. These are two-time-scale algorithms in which the critic uses TD learning with a linear approximation architecture and the actor is updated in an approximate gradient direction based on information provided bythe critic. We show that the features for the critic should span a subspace prescribed by the choice of parameterization of the actor. We conclude by discussing convergence properties and some open problems.

Competition in the wireless telecommunications industry is rampant. To maintain profitability,wireless carriers must control chum, the loss of subscribers who switch from one carrier to another. We explore statistical techniques for chum prediction and, based on these predictions.

In this paper we will treat input selection for a radial basis function (RBF) like classifier within a Bayesian framework. We approximate the a-posteriori distribution over both model coefficients and input subsets by samples drawn with Gibbs updates and reversible jump moves. Using some public datasets, we compare the classification accuracy of the method with a conventional ARD scheme. These datasets are also used to infer the a-posteriori probabilities of different inputsubsets.

A system emulating the functionality of a moving eye-hence the name oculomotor system-has been built and successfully tested.

Department of Cognitive Science University of California, San Diego La Jolla, CA 92093-0515 Abstract Psychophysical and physiological evidence shows that sound localization ofacoustic signals is strongly influenced by their synchrony with visual signals. This effect, known as ventriloquism, is at work when sound coming from the side of a TV set feels as if it were coming from the mouth of the actors. The ventriloquism effect suggests that there is important information about sound location encoded in the synchrony between the audio and video signals. In spite of this evidence, audiovisual synchrony is rarely used as a source of information in computer vision tasks. In this paper we explore the use of audio visual synchrony to locate sound sources.

We first show how to represent sharp posterior probability distributions usingreal valued coefficients on broadly-tuned basis functions. Then we show how the precise times of spikes can be used to convey thereal-valued coefficients on the basis functions quickly and accurately. Finally we describe a simple simulation in which spiking neuronslearn to model an image sequence by fitting a dynamic generative model. 1 Population codes and energy landscapes A perceived object is represented in the brain by the activities of many neurons, but there is no general consensus on how the activities of individual neurons combine to represent the multiple properties of an object. We start by focussing on the case of a single object that has multiple instantiation parameters such as position, velocity, size and orientation. We assume that each neuron has an ideal stimulus in the space of instantiation parameters and that its activation rate or probability of activation falls off monotonically in all directions as the actual stimulus departs from this ideal.

It is known that decision tree learning can be viewed as a form of boosting. However, existing boosting theorems for decision tree learning allow only binary-branching trees and the generalization to multi-branching trees is not immediate. Practical decision tree algorithms, suchas CART and C4.5, implement a tradeoff between the number of branches and the improvement in tree quality as measured by an index function. Here we give a boosting justification fora particular quantitative tradeoff curve. Our main theorem states, in essence, that if we require an improvement proportional to the log of the number of branches then top-down greedy construction ofdecision trees remains an effective boosting algorithm.