A COllective INtelligence (COIN) is a set of interacting reinforcement learning(RL) algorithms designed in an automated fashion so that their collective behavior optimizes a global utility function. We summarize the theory of COINs, then present experiments using thattheory to design COINs to control internet traffic routing. These experiments indicate that COINs outperform all previously investigated RL-based, shortest path routing algorithms. 1 INTRODUCTION COllective INtelligences (COINs) are large, sparsely connected recurrent neural networks, whose "neurons" are reinforcement learning (RL) algorithms. The distinguishing featureof COINs is that their dynamics involves no centralized control, but only the collective effects of the individual neurons each modifying their behavior viatheir individual RL algorithms. This restriction holds even though the goal of the COIN concerns the system's global behavior.

In previous work [6, 9, 10], we advanced a new technique for direct visual matching of images for the purposes of face recognition and image retrieval, using a probabilistic measure of similarity based primarily on a Bayesian (MAP) analysis of image differences, leadingto a "dual" basis similar to eigenfaces [13]. The performance advantage of this probabilistic matching technique over standard Euclidean nearest-neighbor eigenface matching was recently demonstrated using results from DARPA's 1996 "FERET" face recognition competition, in which this probabilistic matching algorithm was found to be the top performer. We have further developed a simple method of replacing the costly compution of nonlinear (online) Bayesian similarity measures by the relatively inexpensive computation of linear (offline) subspace projections and simple (online) Euclidean norms, thus resulting in a significant computational speedup for implementation with very large image databases as typically encountered in real-world applications.

We present a probabilistic method for fusion of images produced by multiple sensors. The approach is based on an image formation model in which the sensor images are noisy, locally linear functions of an underlying, true scene. A Bayesian framework then provides for maximum likelihood or maximum a posteriori estimates of the true scene from the sensor images. Maximum likelihood estimates of the parameters of the image formation model involve (local) second order image statistics, and thus are related to local principal component analysis. We demonstrate the efficacy of the method on images from visible-band and infrared sensors. 1 Introduction Advances in sensing devices have fueled the deployment of multiple sensors in several computational vision systems [1, for example]. Using multiple sensors can increase reliability with respect to single sensor systems.

The initial assumption is that the original data samples lie in the finest space Vo, which is spanned by the scaling function,p E Vo such that the collection {,p( x -t) It E Z} is a Riesz basis of Vo . The first level of the dyadic decomposition then consists of projecting the data samples onto scaling functions which have been dilated to be twice as wide as the original,p.

Te-Won Lee, Michael S. Lewicki and Terrence Sejnowski Howard Hughes Medical Institute Computational Neurobiology Laboratory The Salk Institute 10010 N. Torrey Pines Road La Jolla, California 92037, USA {tewon,lewicki,terry}Osalk.edu Abstract We present an unsupervised classification algorithm based on an ICA mixture model. The ICA mixture model assumes that the observed data can be categorized into several mutually exclusive data classes in which the components in each class are generated by a linear mixture of independent sources. The algorithm finds the independent sources, the mixing matrix for each class and also computes the class membership probability for each data point. This approach extends the Gaussian mixture model so that the classes can have non-Gaussian structure. We demonstrate that this method can learn efficient codes to represent images of natural scenes and text.

Distributed SIPE (DSIPE) is a distributed planning system that provides decision support to human planners in a collaborative planning environment. The key contributions of our research on DSIPE are (1) constraint-based, consistent local views of the global plan that give each planner a view of how other planners' subplans relate to their local planning decisions; (2) methods for automatically identifying and sharing potentially relevant information among distributed planning agents; and (3) techniques for merging subplans that leverage the shared subplan structure to generate a complete, final plan. DSIPE is a fully implemented system and has been demonstrated to end users in the maritime (United States Navy and United States Marine Corps) planning community.

On 30 October 1998, Mihaela Sabin and I ran the Constraint Problem Reformulation Workshop in conjunction with the Fourth International Conference on the Principles and Practices of Constraint Programming held in Pisa, Italy. The goals of the workshop were to discuss the nature of constraint problem reformulation and the benefits and difficulties in reformulating constraint problems and to summarize and understand the recent work in this area.

All regular members is available by writing to ncai@aaai.

In a complex, dynamic multiagent setting, coherent team actions are often jeopardized by conflicts in agents' beliefs, plans, and actions. Despite the considerable progress in teamwork research, the challenge of intrateam conflict resolution has remained largely unaddressed. This article presents CONSA, a system we are developing to resolve conflicts using argumentation-based negotiations. CONSA focuses on exploiting the benefits of argumentation in a team setting. Thus, CONSA casts conflict resolution as a team problem, so that the recent advances in teamwork can be brought to bear during conflict resolution to improve argumentation flexibility. Furthermore, because teamwork conflicts sometimes involve past teamwork, teamwork models can be exploited to provide agents with reusable argumentation knowledge. Additionally, CONSA also includes argumentation strategies geared toward benefiting the team, rather than the individual, and techniques to reduce argumentation overhead.

This article reports on the first phase of the continuous planning and execution framework (CPEF), a system that employs sophisticated plan-generation, -execution, -monitoring, and -repair capabilities to solve complex tasks in unpredictable and dynamic environments. CPEF embraces the philosophy that plans are dynamic, open-ended artifacts that must evolve in response to an ever-changing environment. In particular, plans and activities are updated in response to new information and requirements to ensure that they remain viable and relevant. Users are an integral part of the process, providing input that influences plan generation, repair, and overall system control. CPEF has been applied successfully to generate, execute, and repair complex plans for gaining and maintaining air superiority within a simulated operating environment.