Statistical modeling of nuclear data provides a novel approach to nuclear systematics complementary to established theoretical and phenomenological approaches based on quantum theory. Continuing previous studies in which global statistical modeling is pursued within the general framework of machine learning theory, we implement advances in training algorithms designed to improved generalization, in application to the problem of reproducing and predicting the halflives of nuclear ground states that decay 100% by the beta^- mode. More specifically, fully-connected, multilayer feedforward artificial neural network models are developed using the Levenberg-Marquardt optimization algorithm together with Bayesian regularization and cross-validation. The predictive performance of models emerging from extensive computer experiments is compared with that of traditional microscopic and phenomenological models as well as with the performance of other learning systems, including earlier neural network models as well as the support vector machines recently applied to the same problem. In discussing the results, emphasis is placed on predictions for nuclei that are far from the stability line, and especially those involved in the r-process nucleosynthesis. It is found that the new statistical models can match or even surpass the predictive performance of conventional models for beta-decay systematics and accordingly should provide a valuable additional tool for exploring the expanding nuclear landscape.

We present the Procrustes measure, a novel measure based on Procrustes rotation that enables quantitative comparison of the output of manifold-based embedding algorithms (such as LLE (Roweis and Saul, 2000) and Isomap (Tenenbaum et al, 2000)). The measure also serves as a natural tool when choosing dimension-reduction parameters. We also present two novel dimension-reduction techniques that attempt to minimize the suggested measure, and compare the results of these techniques to the results of existing algorithms. Finally, we suggest a simple iterative method that can be used to improve the output of existing algorithms.

We analyze the performance of a class of manifold-learning algorithms that find their output by minimizing a quadratic form under some normalization constraints. This class consists of Locally Linear Embedding (LLE), Laplacian Eigenmap, Local Tangent Space Alignment (LTSA), Hessian Eigenmaps (HLLE), and Diffusion maps. We present and prove conditions on the manifold that are necessary for the success of the algorithms. Both the finite sample case and the limit case are analyzed. We show that there are simple manifolds in which the necessary conditions are violated, and hence the algorithms cannot recover the underlying manifolds. Finally, we present numerical results that demonstrate our claims.

Past research on probabilistic databases has studied the problem of answering queries on a static database. Application scenarios of probabilistic databases however often involve the conditioning of a database using additional information in the form of new evidence. The conditioning problem is thus to transform a probabilistic database of priors into a posterior probabilistic database which is materialized for subsequent query processing or further refinement. It turns out that the conditioning problem is closely related to the problem of computing exact tuple confidence values. It is known that exact confidence computation is an NP-hard problem. This has led researchers to consider approximation techniques for confidence computation. However, neither conditioning nor exact confidence computation can be solved using such techniques. In this paper we present efficient techniques for both problems. We study several problem decomposition methods and heuristics that are based on the most successful search techniques from constraint satisfaction, such as the Davis-Putnam algorithm. We complement this with a thorough experimental evaluation of the algorithms proposed. Our experiments show that our exact algorithms scale well to realistic database sizes and can in some scenarios compete with the most efficient previous approximation algorithms.

On March 27, 2006, I gave a light-hearted and occasionally bittersweet presentation on “Whatever Happened to AI?” at the Stanford Spring Symposium presentation – to a lively audience of active AI researchers and formerly-active ones (whose current inaction could be variously ascribed to their having aged, reformed, given up, redefined the problem, etc.)  This article is a brief chronicling of that talk, and I entreat the reader to take it in that spirit: a textual snapshot of a discussion with friends and colleagues, rather than a scholarly article. I begin by whining about the Turing Test, but only for a thankfully brief bit, and then get down to my top-10 list of factors that have retarded progress in our field, that have delayed the emergence of a true strong AI.

Humans learn from their mistakes. When things go badly, we notice that something is amiss, figure out what went wrong and why, and attempt to repair the problem. Artificial systems depend on their human designers to program in responses to every eventuality and therefore typically don’t even notice when things go wrong, following their programming over the proverbial, and in some cases literal, cliff. This article describes our past and current work on the Meta-Cognitive Loop, a domain-general approach to giving artificial systems the ability to notice, assess, and repair problems. The goal is to make artificial systems more robust and less dependent on their human designers.

In response, AI the poster's size, artistic constraints, Magazine has developed a poster to and diversity of perspectives, not all help educate students, faculty, and the suggestions could be included in the public about AI and to spur them to final design, but all were greatly appreciated. I also thank AAAI, the National The poster's design was based on Science Foundation, Microsoft input from experts on how to convey Research, and Yahoo!Research for their key aspects of AI and to capture the generous support. The are included at the poster web design does not attempt the impossible site, www.aaai.org/AILandscape.php. Nor does it present a list of new support of the poster project, especially advances, which would soon become Mike Hamilton, whose many contributions obsolete. Instead, it presents a snapshot played a key role throughout. of a few aspects of AI selected to catalyze interest and to prompt viewers The poster was designed by James to find out more by exploring AAAI Gary, of Brooklyn, New York.

Human-Robot Interaction (HRI-2008) with robots," highlights the importance It also featured Foundation, and the European a panel on "robo-ethics" intended Network for the Advancement of Artificial to start a discussion of the ethical Cognitive Systems (EU Cognition) and societal implications of provided grants. More than 250 autonomous robots and a panel on representatives from academia, government, "what is HRI?" that examined the constitutive and industry attended HRI-components of human-robot 2008. HRI is the premier forum for the Of the 134 submissions, the program presentation and discussion of committee accepted 48 full research results in human-robot interaction. Human-robot interaction 27 submissions) were featured in a special is inherently interdisciplinary session. The workshops artificial intelligence, cognitive science, addressed metrics (an examination of ergonomics, human-computer proposed guidelines for evaluating interaction, psychology, robotics, and HRI), coding behavioral video data other fields. From 1997 to 2000, he was vice president of development for Fourth Planet, Inc., a developer of real-time visualization software. Fong has published more than 50 papers in field robotics, human-robot interaction, virtual reality user interfaces, and parallel processing, was chair of the 2006 AAAI Spring Symposium on human-robot interaction in space, and is cogeneral chair for HRI-2008. Kerstin Dautenhahn is the research professor of artificial intelligence in the School of Computer Science and coordinator of the Adaptive Systems Research Group at the University of Hertfordshire in the United Kingdom. Save the Date! -- July 11-15, 2010 AAAI comes to Atlanta, Georgia in 2010! Please mark your calendars, and visit www. She was general chair of IEEE RO-MAN06 and cogeneral chair of HRI-2008. Scheutz was the coprogram chair for HRI-Seven student teams competed to award went to "Robots in Organizations: University of Amsterdam took top Jodi Forlizzi.

Software personal assistants continue to be a topic of significant research interest. This article outlines some of the important lessons learned from a successfully-deployed team of personal assistant agents (Electric Elves) in an office environment. In the Electric Elves project, a team of almost a dozen personal assistant agents were continually active for seven months. Each elf (agent) represented one person and assisted in daily activities in an actual office environment. This project led to several important observations about privacy, adjustable autonomy, and social norms in office environments. In addition to outlining some of the key lessons learned we outline our continued research to address some of the concerns raised.

It seemed miraculous at the time; a situated automaton that knew things without needing any models. However, I thought of it as (sensor-driven) feedback control, versus (plan driven, eyes shut) feed-forward control. I then used Mike Georgeff's procedural reasoning system (PRS) to make Flakey not only drive but navigate an office building. In some respects this project succeeded: the robot's "domain knowledge" was nothing more than a static connection graph--no distances to drive, no widths of halls or doorways, no a priori obstacles--such information was acquired en route from sensory input. In other respects, however, progress was unsatisfying.