We present a series of theoretical arguments supporting the claim that a large class of modern learning algorithms that rely solely on the smoothness prior-with similarity between examples expressed with a local kernel - are sensitive to the curse of dimensionality, or more precisely to the variability of the target. Our discussion covers supervised, semisupervised andunsupervised learning algorithms. These algorithms are found to be local in the sense that crucial properties of the learned function atx depend mostly on the neighbors of x in the training set. This makes them sensitive to the curse of dimensionality, well studied for classical nonparametric statistical learning. We show in the case of the Gaussian kernel that when the function to be learned has many variations, these algorithms require a number of training examples proportional to the number of variations, which could be large even though there may exist shortdescriptions of the target function, i.e. their Kolmogorov complexity maybe low. This suggests that there exist non-local learning algorithms that at least have the potential to learn about such structured but apparently complex functions (because locally they have many variations), whilenot using very specific prior domain knowledge.

(MDAI 2007).

We Papers submitted to the II track should For a complete list of deadlines, program are delighted to announce this permanent highlight synergistic effects of integrating information, and to check for change as we expand the venue components from distinct areas further updates, please visit the AAAIfor the conference throughout the of AI to achieve intelligent behavior.

The celebration then moved to web and integrated intelligence, as on Artificial Intelligence and Boston where a huge turnout of AAAI well as the nectar and senior member the Nineteenth Innovative Applications fellows--from founding luminaries to papers, is a significant factor in this of Artificial Intelligence Conference 2006 fellow inductees--reported a trend." Senior member papers are a commemorated fifty years of great weekend meeting prior to the way to collect reflections about areas artificial intelligence research in AAAI conference full of discussions of work by leaders in the field.

The Workshop program of the Twenty-First Conference on Artificial Intelligence was held July 16-17, 2006 in Boston, Massachusetts. The program was chaired by Joyce Chai and Keith Decker. The titles of the 17 workshops were AIDriven Technologies for Service-Oriented Computing; Auction Mechanisms for Robot Coordination; Cognitive Modeling and Agent-Based Social Simulations, Cognitive Robotics; Computational Aesthetics: Artificial Intelligence Approaches to Beauty and Happiness; Educational Data Mining; Evaluation Methods for Machine Learning; Event Extraction and Synthesis; Heuristic Search, Memory- Based Heuristics, and Their Applications; Human Implications of Human-Robot Interaction; Intelligent Techniques in Web Personalization; Learning for Search; Modeling and Retrieval of Context; Modeling Others from Observations; and Statistical and Empirical Approaches for Spoken Dialogue Systems.

This is a wonderful opportunity, yet a position is very hard to match in any other. The first AAAI conference was held at Stanford University; it was very much a research conference, a scientific event that generated a lot of excitement. The conference was small and intimate, with few parallel sessions. There were excellent opportunities for us to talk to one another. AAAI-80 gave real substance to the organization, clearly getting AAAI off on the right foot, and it gave new identity and cohesiveness to the field. This year--2006--has also been a big year, celebrating the 50th anniversary of the original meeting at Dartmouth College, where the name "artificial intelligence" first came into common use. Numerous events around the world, including a celebratory symposium at Dartmouth and an AAAI Fellows Symposium associated with AAAI-05, have marked this important milestone in the history of the field. Progress since our first AAAI conference has The First AAAI Conference was Held at Stanford University. While each year's results may have seemed incremental, when we look back over the entire period we see some truly amazing plate the big picture and, perhaps more importantly things. In job at DARPA), to identify gaps in our national hindsight this may no longer look so exciting computing research agenda. It also occurred to (purists will say that it was not an "AI" system me that that perspective was a very special that beat Garry Kasparov but rather a highly asset to use in drafting this presidential engineered special-purpose machine largely address. Looking forward from back then, no want to raise a broad issue and consider matter how Deep Blue actually worked, playing some larger questions regarding the nature of chess well was clearly an AI problem--in fact, a the field itself and the role that AAAI as an classical one--and our success was historic.

In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like ``after", which overtly signal a temporal relation. We first show that models trained on main and subordinate clauses connected with a temporal marker achieve good performance on a pseudo-disambiguation task simulating temporal inference (during testing the temporal marker is treated as unseen and the models must select the right marker from a set of possible candidates). Secondly, we assess whether the proposed approach holds promise for the semi-automatic creation of temporal annotations. Specifically, we use a model trained on noisy and approximate data (i.e., main and subordinate clauses) to predict intra-sentential relations present in TimeBank, a corpus annotated rich temporal information. Our experiments compare and contrast several probabilistic models differing in their feature space, linguistic assumptions and data requirements. We evaluate performance against gold standard corpora and also against human subjects.

Rob Miller (Massachusetts Institute of Technology) will be held July 22-26, 2007 in Vancouver, Holger Hoos (University of British Columbia) British Columbia, Canada.

Distributed Sensor Networks (DSN) Computers and Advanced Technology Symposium. Paper submission is required by November 8, 2006.

This paper presents a new framework for anytime heuristic search where the task is to achieve as many goals as possible within the allocated resources. We show the inadequacy of traditional distance-estimation heuristics for tasks of this type and present alternative heuristics that are more appropriate for multiple-goal search. In particular, we introduce the marginal-utility heuristic, which estimates the cost and the benefit of exploring a subtree below a search node. We developed two methods for online learning of the marginal-utility heuristic. One is based on local similarity of the partial marginal utility of sibling nodes, and the other generalizes marginal-utility over the state feature space. We apply our adaptive and non-adaptive multiple-goal search algorithms to several problems, including focused crawling, and show their superiority over existing methods.