People can understand complex auditory and visual information, often using one to disambiguate the other. Automated analysis, even at a lowlevel, facessevere challenges, including the lack of accurate statistical models for the signals, and their high-dimensionality and varied sampling rates.Previous approaches [6] assumed simple parametric models for the joint distribution which, while tractable, cannot capture the complex signalrelationships. We learn the joint distribution of the visual and auditory signals using a nonparametric approach. First, we project the data into a maximally informative, low-dimensional subspace, suitable for density estimation. These learned densities allow processing across signal modalities.

We introduce a new, nonparametric and principled, distance based clustering method. This method combines a pairwise based approach witha vector-quantization method which provide a meaningful interpretation to the resulting clusters. The idea is based on turning the distance matrix into a Markov process and then examine the decay of mutual-information during the relaxation of this process. The clusters emerge as quasi-stable structures during thisrelaxation, and then are extracted using the information bottleneck method.

Theories of object recognition often assume that only one representation schemeis used within one visual-processing pathway. Versatility of the visual system comes from having multiple visual-processing pathways, each specialized in a different category of objects. We propose a theoretically simpler alternative, capable of explaining the same set of data and more. A single primary visual-processing pathway, loosely modular, is assumed. Memory modules are attached to sites along this pathway.

For example, priming in a subliminal perception task was found to be confined to a quadrant of the visual field [16]. The notion that the representation of an object may be tied to a particular location in the visual field where it is first observed is compatible with the concept of object file, a hypothetical record created by the visual system for every encountered object, which persists as long as the object is observed. Moreover, location (as it figures in the CoF model) should be interpreted relative to the focus of attention, rather than retinotopically [17]. The idea that global relationships (hence, large-scale structure) have precedence over local ones [18], which is central to our approach, has withstood extensive testing in the past two decades. Even with the perceptual salience of the global and local structure equated, subjects are able to process the relations among elements before the elements themselves are identified [19]. More generally, humans are limited in their ability to represent spatial structure, in that the representation of spatial relations requires spatial attention. For example, visual search is difficult when above below 0. 9

We develop an approach to object recognition based on matching shapesand using a resulting measure of similarity in a nearest neighbor classifier. The key algorithmic problem here is that of finding pointwise correspondences between an image shape and a stored prototype shape. We introduce a new shape descriptor, the shape context, which makes this possible, using a simple and robust algorithm. We demonstrate that shape contexts greatly simplify recovery of correspondences between points of two given shapes. Once shapes are aligned, shape contexts are used to define a robust score for measuring shape similarity.

Learning a complex task can be significantly facilitated by defining a hierarchy of subtasks. An agent can learn to choose between various temporally abstract actions, each solving an assigned subtask, to accomplish theoverall task. In this paper, we study hierarchical learning using the framework of options. We argue that to take full advantage of hierarchical structure,one should perform option-specific state abstraction, and that if this is to scale to larger tasks, state abstraction should be automated. Weadapt McCallum's U-Tree algorithm to automatically build option-specific representations of the state feature space, and we illustrate theresulting algorithm using a simple hierarchical task. Results suggest that automated option-specific state abstraction is an attractive approach to making hierarchical learning systems more effective.

To control the walking gaits of a four-legged robot we present a novel neuromorphic VLSI chip that coordinates the relative phasing of the robot's legs similar to how spinal Central Pattern Generators are believed to control vertebrate locomotion [3]. The chip controls the leg movements bydriving motors with time varying voltages which are the outputs of a small network of coupled oscillators. The characteristics of the chip's output voltages depend on a set of input parameters.

A Bayes network based classifier for distinguishing terrestrial rocks from meteorites is implemented onboard the Nomad robot. Equipped with a camera, spectrometer and eddy current sensor, this robot searched the ice sheets of Antarctica and autonomously made the first robotic identification of a meteorite, in January 2000 at the Elephant Moraine. This paper discusses rock classification from a robotic platform, and describes the system onboard Nomad. 1 Introduction Figure 1: Human meteorite search with snowmobiles on the Antarctic ice sheets, and on foot in the moraines. Antarctica contains the most fertile meteorite hunting grounds on Earth. The pristine, dry and cold environment ensures that meteorites deposited there are preserved for long periods.

Nearest neighbor classification assumes locally constant class conditional probabilities.This assumption becomes invalid in high dimensions with finite samples due to the curse of dimensionality. Severe bias can be introduced under these conditions when using the nearest neighbor rule. We propose a locally adaptive nearest neighbor classification method to try to minimize bias. We use a Chi-squared distance analysis to compute a flexible metric for producing neighborhoodsthat are elongated along less relevant feature dimensions and constricted along most influential ones. As a result, the class conditional probabilities tend to be smoother in the modified neighborhoods,whereby better classification performance can be achieved. The efficacy of our method is validated and compared against other techniques using a variety of real world data. 1 Introduction

The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product of experts network. Network parameters are learned online using a modified SARSA algorithm which minimizes the inconsistency of the Q-values of consecutive state-action pairs. Actions arechosen based on the current value estimates by fixing the current state and sampling actions from the network using Gibbs sampling. The algorithm is tested on a cooperative multi-agent task. The product of experts model is found to perform comparably to table-based Q-Iearning for small instances of the task, and continues to perform well when the problem becomes too large for a table-based representation.