The Association for the Advancement of Artificial Intelligence was pleased to present the 2011 Fall Symposium Series, held Friday through Sunday, November 4–6, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the seven symposia are as follows: (1) Advances in Cognitive Systems; (2) Building Representations of Common Ground with Intelligent Agents; (3) Complex Adaptive Systems: Energy, Information and Intelligence; (4) Multiagent Coordination under Uncertainty; (5) Open Government Knowledge: AI Opportunities and Challenges; (6) Question Generation; and (7) Robot-Human Teamwork in Dynamic Adverse Environment. The highlights of each symposium are presented in this report.

According to a 2008 OECD review of national policies for education in South Africa, typically only 15 percent to 18 percent of secondary school students who sit for their final year exams every year qualify automatically for university-level education; and this number seems to be decreasing as more students choose to complete subjects on so-called standard grade instead of higher grade, a trend that is especially apparent for mathematics and science, the two fields with critical skills shortages in the country. The South African tertiary education sector is quite small for a country with a population of around 50 million, with 11 "traditional" universities, 6 technical universities, and 6 comprehensive universities. The latter university types focus on more technical or vocational education. The public sector also funds 16 research institutions. In spite of these obstacles, South African universities participate in world-class research activities in many fields and range among the best on the African continent.

Posters, the AAAI/SIGART Doctoral of AAAI; submit papers to the conference Consortium, and more!

Of course, this is far from the first attempt to plot a course toward human-level AGI: arguably this was the goal of the founders of the field of artificial intelligence in the 1950s, and has been pursued by a steady stream of AI researchers since, even as the majority of the AI field has focused its attention on more narrow, specific subgoals. The ideas presented here build on the ideas of others in innumerable ways, but to review the history of AI and situate the current effort in the context of its predecessors would require a much longer article than this one. Thus we have chosen to focus on the results of our AGI roadmap discussions, acknowledging in a broad way the many debts owed to many prior researchers. References to the prior literature on evaluation of advanced AI systems are given by Laird (Laird et al. 2009) and Geortzel and Bugaj (2009), which may in a limited sense be considered prequels to this article. We begin by discussing AGI in general and adopt a pragmatic goal for measuring progress toward its attainment. An initial capability landscape for AGI The heterogeneity of general intelligence in will be presented, drawing on major themes from humans makes it practically impossible to develop developmental psychology and illuminated by a comprehensive, fine-grained measurement system mathematical, physiological, and informationprocessing for AGI. While we encourage research in defining perspectives. The challenge of identifying such high-fidelity metrics for specific capabilities, appropriate tasks and environments for measuring we feel that at this stage of AGI development AGI will be taken up. Several scenarios will a pragmatic, high-level goal is the best we can be presented as milestones outlining a roadmap agree upon. I advocate beginning with a system that has minimal, although extensive, built-in capabilities. Many variant approaches have been proposed A classic example of the narrow AI approach was for achieving such a goal, and both the AI and AGI IBM's Deep Blue system (Campbell, Hoane, and communities have been working for decades on Hsu 2002), which successfully defeated world chess the myriad subgoals that would have to be champion Gary Kasparov but could not readily achieved and integrated to deliver a comprehensive apply that skill to any other problem domain without AGI system.

On the day before the exhibition the participants convened a workshop of 18 short talks. Each track's exhibitors presented a summary of their exhibit. In addition, four guest speakers provided a broader context for all of the exhibitors' efforts. The first guest speaker was the National Science Foundation's Sven Koenig, who highlighted several federal programs that support projects in embodied intelligence. Koenig also provided insights into some of these program's specific priorities, such as international collaborations and educational engagement.

The problem of joint feature selection across a group of related tasks has applications in many areas including biomedical informatics and computer vision. We consider the l2,1-norm regularized regression model for joint feature selection from multiple tasks, which can be derived in the probabilistic framework by assuming a suitable prior from the exponential family. One appealing feature of the l2,1-norm regularization is that it encourages multiple predictors to share similar sparsity patterns. However, the resulting optimization problem is challenging to solve due to the non-smoothness of the l2,1-norm regularization. In this paper, we propose to accelerate the computation by reformulating it as two equivalent smooth convex optimization problems which are then solved via the Nesterov's method-an optimal first-order black-box method for smooth convex optimization. A key building block in solving the reformulations is the Euclidean projection. We show that the Euclidean projection for the first reformulation can be analytically computed, while the Euclidean projection for the second one can be computed in linear time. Empirical evaluations on several data sets verify the efficiency of the proposed algorithms.

In a typical online learning scenario, a learner is required to process a large data stream using a small memory buffer. Such a requirement is usually in conflict with a learner's primary pursuit of prediction accuracy. To address this dilemma, we introduce a novel Bayesian online classi cation algorithm, called the Virtual Vector Machine. The virtual vector machine allows you to smoothly trade-off prediction accuracy with memory size. The virtual vector machine summarizes the information contained in the preceding data stream by a Gaussian distribution over the classi cation weights plus a constant number of virtual data points. The virtual data points are designed to add extra non-Gaussian information about the classi cation weights. To maintain the constant number of virtual points, the virtual vector machine adds the current real data point into the virtual point set, merges two most similar virtual points into a new virtual point or deletes a virtual point that is far from the decision boundary. The information lost in this process is absorbed into the Gaussian distribution. The extra information provided by the virtual points leads to improved predictive accuracy over previous online classification algorithms.

Many applications of causal analysis call for assessing, retrospectively, the effect of withholding an action that has in fact been implemented. This counterfactual quantity, sometimes called "effect of treatment on the treated," (ETT) have been used to to evaluate educational programs, critic public policies, and justify individual decision making. In this paper we explore the conditions under which ETT can be estimated from (i.e., identified in) experimental and/or observational studies. We show that, when the action invokes a singleton variable, the conditions for ETT identification have simple characterizations in terms of causal diagrams. We further give a graphical characterization of the conditions under which the effects of multiple treatments on the treated can be identified, as well as ways in which the ETT estimand can be constructed from both interventional and observational distributions.

We present the discrete infinite logistic normal distribution (DILN), a Bayesian nonparametric prior for mixed membership models. DILN is a generalization of the hierarchical Dirichlet process (HDP) that models correlation structure between the weights of the atoms at the group level. We derive a representation of DILN as a normalized collection of gamma-distributed random variables, and study its statistical properties. We consider applications to topic modeling and derive a variational inference algorithm for approximate posterior inference. We study the empirical performance of the DILN topic model on four corpora, comparing performance with the HDP and the correlated topic model (CTM). To deal with large-scale data sets, we also develop an online inference algorithm for DILN and compare with online HDP and online LDA on the Nature magazine, which contains approximately 350,000 articles.

In distributed learning, the goal is to perform a learning task over data distributed across multiple nodes with minimal (expensive) communication. Prior work (Daume III et al., 2012) proposes a general model that bounds the communication required for learning classifiers while allowing for $\eps$ training error on linearly separable data adversarially distributed across nodes. In this work, we develop key improvements and extensions to this basic model. Our first result is a two-party multiplicative-weight-update based protocol that uses $O(d^2 \log{1/\eps})$ words of communication to classify distributed data in arbitrary dimension $d$, $\eps$-optimally. This readily extends to classification over $k$ nodes with $O(kd^2 \log{1/\eps})$ words of communication. Our proposed protocol is simple to implement and is considerably more efficient than baselines compared, as demonstrated by our empirical results. In addition, we illustrate general algorithm design paradigms for doing efficient learning over distributed data. We show how to solve fixed-dimensional and high dimensional linear programming efficiently in a distributed setting where constraints may be distributed across nodes. Since many learning problems can be viewed as convex optimization problems where constraints are generated by individual points, this models many typical distributed learning scenarios. Our techniques make use of a novel connection from multipass streaming, as well as adapting the multiplicative-weight-update framework more generally to a distributed setting. As a consequence, our methods extend to the wide range of problems solvable using these techniques.