This paper revisits the problem of analyzing multiple ratings given by different judges. Different from previous work that focuses on distilling the true labels from noisy crowdsourcing ratings, we emphasize gaining diagnostic insights into our in-house well-trained judges. We generalize the well-known DawidSkene model (Dawid & Skene, 1979) to a spectrum of probabilistic models under the same "TrueLabel + Confusion" paradigm, and show that our proposed hierarchical Bayesian model, called HybridConfusion, consistently outperforms DawidSkene on both synthetic and real-world data sets.

Much of current machine learning (ML) research has lost its connection to problems of import to the larger world of science and society. From this perspective, there exist glaring limitations in the data sets we investigate, the metrics we employ for evaluation, and the degree to which results are communicated back to their originating domains. What changes are needed to how we conduct research to increase the impact that ML has? We present six Impact Challenges to explicitly focus the field?s energy and attention, and we discuss existing obstacles that must be addressed. We aim to inspire ongoing discussion and focus on ML that matters.

Portfolio planners and parameter tuning are two ideas that have recently attracted significant attention in the domain-independent planning community. We combine these two ideas and present a portfolio planner that runs automatically configured planners. We let the automatic parameter tuning framework ParamILS find fast configurations of the Fast Downward planning system for a number of planning domains. Afterwards we learn a portfolio of those planner configurations. Evaluation of our portfolio planner on the IPC 2011 domains shows that it has a significantly higher IPC score than the winner of the sequential satisficing track.

This work describes an approach that automatically extracts standard metadata information from e-learning contents, combines it with the student preferences/goals and creates PDDL planning domains+problems.These PDDL problems can be solved by current planners, although we motivate the use and benefits of case-based planning techniques, to obtain fully tailored learning routes that significantly enhance the learning process. During the execution of a given route, a monitoring phase is used to detect discrepancies, i.e. flaws that prevent the student from continuing with the original plan. In such a situation, an adaptation mechanism becomes necessary to fix the flaws, while also trying to minimise the differences between the original and the new route. We have integrated this approach on top of Moodle and experimented with 100 benchmark problems to evaluate the quality, scalability and viability of the system.

From this excellent collection of papers, three for presentation at ICAPS 2012, the were selected for special recognition. ICAPS continues Nguyen, Vien Tran, Tran Cao Son and Enrico the traditional high standards of AIPS and ECP Pontelli were selected for Best Student Paper as an archival forum for new research in the Award. In addition to the oral presentation of these e 45 papers included in this volume, consisting papers, the technical program of this year's of 37 long papers and 8 short papers, are ICAPS conference includes invited talks by those selected for plenary presentation at three distinguished speakers: Robert O. Ambrose ICAPS 2012 from a total of 132 submissions. Topics under various constraints and assumptions, included real-time planning, planning in mixed to empirical evaluation of planning and discrete-continuous domains, planning for systems scheduling techniques in practical applications. Papers in the subareas of optimal planning, probabilistic were encouraged from a range of neighboring and non-deterministic planning, planning disciplines, including model-based and scheduling for transportation, robot path reasoning, hybrid systems, run-time verification, planning, and new developments in heuristics control and robotics.

We study the generalization performance of online learning algorithms trained on samples coming from a dependent source of data. We show that the generalization error of any stable online algorithm concentrates around its regret--an easily computable statistic of the online performance of the algorithm--when the underlying ergodic process is $\beta$- or $\phi$-mixing. We show high probability error bounds assuming the loss function is convex, and we also establish sharp convergence rates and deviation bounds for strongly convex losses and several linear prediction problems such as linear and logistic regression, least-squares SVM, and boosting on dependent data. In addition, our results have straightforward applications to stochastic optimization with dependent data, and our analysis requires only martingale convergence arguments; we need not rely on more powerful statistical tools such as empirical process theory.

Social causality is the inference an entity makes about the social behavior of other entities and self. Besides physical cause and effect, social causality involves reasoning about epistemic states of agents and coercive circumstances. Based on such inference, responsibility judgment is the process whereby one singles out individuals to assign responsibility, credit or blame for multi-agent activities. Social causality and responsibility judgment are a key aspect of social intelligence, and a model for them facilitates the design and development of a variety of multi-agent interactive systems. Based on psychological attribution theory, this paper presents a domain-independent computational model to automate social inference and judgment process according to an agents causal knowledge and observations of interaction. We conduct experimental studies to empirically validate the computational model. The experimental results show that our model predicts human judgments of social attributions and makes inferences consistent with what most people do in their judgments. Therefore, the proposed model can be generically incorporated into an intelligent system to augment its social and cognitive functionality.

High throughput genetic sequencing arrays with thousands of measurements per sample and a great amount of related censored clinical data have increased demanding need for better measurement specific model selection. In this paper we establish strong oracle properties of nonconcave penalized methods for nonpolynomial (NP) dimensional data with censoring in the framework of Cox's proportional hazards model. A class of folded-concave penalties are employed and both LASSO and SCAD are discussed specifically. We unveil the question under which dimensionality and correlation restrictions can an oracle estimator be constructed and grasped. It is demonstrated that nonconcave penalties lead to significant reduction of the "irrepresentable condition" needed for LASSO model selection consistency. The large deviation result for martingales, bearing interests of its own, is developed for characterizing the strong oracle property. Moreover, the nonconcave regularized estimator, is shown to achieve asymptotically the information bound of the oracle estimator. A coordinate-wise algorithm is developed for finding the grid of solution paths for penalized hazard regression problems, and its performance is evaluated on simulated and gene association study examples.

Psychosocial assessments and treatments are effective for a range of psychological problems.One particular area of concern is youth suicide. This paper reports on the SAMHT intelligent tutoring system, which provides youth suicide risk assessment training.SAMHT's interactive avatar interface is based on an intelligent backend, and provides a believable interaction that is effective for training mental health professionals.

Reading tutors can provide an unprecedented opportunity to collect and analyze large amounts of data for understanding how students learn. We trained models of oral reading prosody (pitch, intensity, and duration) on a corpus of narrations of 4558 sentences by 11 fluent adults. We used these models to evaluate the oral reading prosody of 85,209 sentences read by 55 children (mostly) 7-10 years old who used Project LISTEN's Reading Tutor during the 2005-2006 school year. We mined the resulting data to pinpoint the specific common syntactic and lexical features of text that children scored best and worst on. These features predict their fluency and comprehension test scores and gains better than previous models. Focusing on these features may help human or automated tutors improve children’s fluency and comprehension more effectively.