We take a conversational character trained on a set of linked question-answer pairs authored by hand, and augment its training data by adding sets of question-answer pairs which are generated automatically from texts on different topics. The augmented characters can answer questions about the new topics, at the cost of some performance loss on questions about the topics that the original character was trained to answer.

This paper documents a functionality-driven exploration of automatic working-memory management in Soar. We first derive and discuss desiderata that arise from the need to embed a mechanism for managing working memory within a general cognitive architecture that is used to develop real-time agents. We provide details of our mechanism, including the decay model and architecture-independent data structures and algorithms that are computationally efficient. Finally, we present empirical results, which demonstrate both that our mechanism performs with little computational overhead and that it helps maintain the reactivity of a Soar agent contending with long-term, autonomous simulated robotic exploration as it reasons using large amounts of acquired information.

In this paper we describe a complex adaptive systems model of interactions between coupled human and natural system. We use learning classifier systems to create adaptive agents in a simulation of the Maine lobster fishery to explore the relationships among ecological, economic, and social characteristics. Our hypothesis is that the cost of information and learning drives agents' decisions to compete or co-operate and, consequently, the emergence of long-term relationships. Initial results provide tentative support for the hypothesis and the ability of this model to provide insight into the dynamics of individual interactions and the social relationships that emerge from those interactions.

The Betty’s Brain computer-based learning system provides an open-ended and choice-rich environment for science learning. Using the learning-by-teaching paradigm paired with feedback and support provided by two pedagogical agents, the system also promotes the development of self-regulated learning strategies to support preparation for future learning. We apply metacognitive learning theories and experiential analysis to interpret the results from previous classroom studies. We propose an integrated cognitive and metacognitive model for effective, self-regulated student learning in the Betty’s Brain environment, and then apply this model to interpret and analyze common suboptimal learning strategies students apply during their learning. This comparison is used to derive feedback for helping learners overcome these difficulties and adopt more effective strategies for regulating their learning. Preliminary results demonstrate that students who were responsive to the feedback had better learning performance.

The literature on conceptual blending and metaphor-making has illustrations galore of how these mechanisms may support the creation and grounding of new concepts (or whole domains) in terms of a complex, integrated network of older ones. In spite of this, as of yet there is no general computational account of blending and metaphor-making that has proven powerful enough as to cover all the examples from the literature. This paper proposes a logic-based framework for blending and metaphor making and explores its applicability in settings as diverse as mathematical domain formation, classical rationality puzzles, and noun-noun combinations.

Reasoning with commonsense science knowledge is an important challenge for Artificial Intelligence. This paper presents a system that revises its knowledge in a commonsense science domain by constructing and evaluating explanations. Domain knowledge is represented using qualitative model fragments, which are used to explain phenomena via model formulation. Metareasoning is used to (1) score competing explanations numerically along several dimensions and (2) evaluate preferred explanations for global consistency. Inconsistencies cause the system to favor alternative explanations and thereby change its beliefs. We simulate the belief changes of several students during clinical interviews about how the seasons change. We show that qualitative models accurately represent student knowledge and that our system produces and revises a sequence of explanations similar those of the students.

Web Effort Estimation is a process of predicting the efforts and cost in terms of money, schedule and staff for any software project system. Many estimation models have been proposed over the last three decades and it is believed that it is a must for the purpose of: Budgeting, risk analysis, project planning and control, and project improvement investment analysis. In this paper, we investigate the use of Fuzzy ID3 decision tree for software cost estimation; it is designed by integrating the principles of ID3 decision tree and the fuzzy set-theoretic concepts, enabling the model to handle uncertain and imprecise data when describing the software projects, which can improve greatly the accuracy of obtained estimates. MMRE and Pred are used as measures of prediction accuracy for this study. A series of experiments is reported using two different software projects datasets namely, Tukutuku and COCOMO'81 datasets. The results are compared with those produced by the crisp version of the ID3 decision tree.

We present a new algorithm for probabilistic planning with no observability. Our algorithm, called Probabilistic-FF, extends the heuristic forward-search machinery of Conformant-FF to problems with probabilistic uncertainty about both the initial state and action effects. Specifically, Probabilistic-FF combines Conformant-FFs techniques with a powerful machinery for weighted model counting in (weighted) CNFs, serving to elegantly define both the search space and the heuristic function. Our evaluation of Probabilistic-FF shows its fine scalability in a range of probabilistic domains, constituting a several orders of magnitude improvement over previous results in this area. We use a problematic case to point out the main open issue to be addressed by further research.

With the recent dramatic transformations in the world of digital music, a music listener is now just a couple of clicks away from being able to listen to nearly any song that has ever been recorded. With so much music readily available, tools that help a user find new, interesting music that matches her taste become increasingly important. In this article we explore one such tool: music recommendation. We describe common music recommendation use cases such as finding new artists, finding others with similar listening taste, and generating interesting music playlists. We describe the various approaches currently being explored by practitioners to satisfy these use cases. Finally, we show how results of three different music recommendation technologies compare when applied to the task of finding similar artists to a seed artist.

This year, the Robotics Exhibition included two such robotics challenge problems: manipulation and learning by demonstration. In the Small-Scale Manipulation Challenge four teams demonstrated systems playing robotic chess. This exhibit was organized by David Touretzky and Monica D. Anderson. In the Learning by Demonstration Challenge, three teams demonstrated systems learning a block-sorting task. This exhibit was organized by Sonia Chernova. Additionally, this year marked another successful turnout for the Robotics Education Track, organized by Zachary Dodds, which highlights student-and educator-led robotics projects. In this article we give a summary of these three components of the exhibition.