This was a large applied research effort that presented many opportunities for unusual experiences. In one such experience, I was called in, at the last minute, to help improve our ALV proposal. The proposal was a 300-page document that segued smoothly from problem description to corporate capabilities and managerial plan, omitting any mention of technical approach. This taught me a rule of thumb I have seen validated many times: the larger the project (in dollars and scope), the poorer the technical proposal. In a second experience, I was demonstrating a dynamic programming algorithm at a quarterly review.

The Seventeenth International Conference on Automated Planning and Scheduling (ICAPS-07) was held in Providence, Rhode Island, in September 2007. It covered the latest theoretical and practical advances in planning and scheduling. The conference was collocated with the Thirteenth International Conference on Principles and Practice of Constraint Programming (CP-07). The program consisted of tutorials, workshops, system demonstrations, a doctoral consortium, and three days of technical presentations mostly in parallel sessions. ICAPS-07 also hosted the second edition of the International Competition on Knowledge Engineering for Planning and Scheduling.

Over the last few years, a number of areas of natural language processing have begun applying graph-based techniques. These include, among others, text summarization, syntactic parsing, word-sense disambiguation, ontology construction, sentiment and subjectivity analysis, and text clustering. In this paper, we present some of the most successful graph-based representations and algorithms used in language processing and try to explain how and why they work. Since the early ages of artificial intelligence, associative or semantic networks have been proposed as representations that enable the storage of such language units and the relations that interconnect them and that allow for a variety of inference and reasoning processes, simulating some of the functionalities of the human mind. The symbolic structures that emerge from these representations correspond naturally to graphs--where text constituents are represented as vertices and their interconnecting relations form the edges in the graph.

The map is composed of thousands of scene locations, and for each location there are tens of different images of varying quality to choose from. Constraints and preferences on map quality make it desirable to develop an automated solution to the map-generation problem. This article formulates a global map-generator problem as a constraint-optimization problem (GMG-COP) and describes an approach to solving it using local search. The article also describes the integration of a GMG solver into a graphical user interface for visualizing and comparing solutions, thus allowing for solutions to be generated with human participation and guidance. Data Center to produce a high-resolution mosaic map of the Earth.

More than 40,000 learners worldwide have used TLCTS courses. TLCTS utilizes artificial intelligence technologies during the authoring process and at run time to process learner speech, engage in dialogue, and evaluate and assess learner performance. This paper describes the architecture of TLCTS and the artificial intelligence technologies that it employs and presents results from multiple evaluation studies that demonstrate the benefits of learning foreign language and culture using this approach. It includes interactive lessons that focus on particular communicative skills and interactive games that apply those skills. Heavy emphasis is placed on spoken communication: learners must learn to speak the foreign language to complete the lessons and play the games.

"Solving Large-Scale Constraint Satisfaction and Scheduling Problems Using a Heuristic Repair Method," by Steve Minton, Mark Johnston, Andy Phillips, and Phil Laird clearly achieved both. It proved that local search and repair was applicable to a wide class of constraint-satisfaction problems and clearly explicated the theory behind that proof. The work epitomizes the guiding philosophy of that laboratory: AI research can simultaneously advance the state of the art and provide practical solutions to key problems faced by the Space Agency and its collaborators. Minton and colleagues developed a heuristic repair method, called "min-conflicts" for solving large-scale constraint-satisfaction problems (CSP), with a particular focus on massive scheduling tasks. Mark Johnston, an astronomer and computer scientist from the Space Telescope Science Institute at Johns Hopkins, served simultaneously as domain expert and codeveloper.

As evidenced by the articles in this special issue, transfer learning has come a long way in the past five or so years, partially because of DARPA's Transfer Learning program, which sponsored much of the work reported in this issue. There is a Transfer Learning Toolkit for Matlab available on the web. Transfer learning has developed techniques for classification, regression, and clustering (as summarized in Pan and Yang's 2009 survey) and for complex interactive tasks that are often best addressed by reinforcement learning techniques. However, there is a more practical and more feasible goal for transfer learning against which progress is being made. An engineering-oriented goal of artificial intelligence that could be enabled by transfer learning is the ability to construct a large number of diverse applications not from scratch, but by taking advantage of knowledge already acquired and formally represented for other purposes.

Its goal is to capture, in a general form, the internal structure of the objects, relations, strategies, and processes used to solve tasks drawn from a source domain, and exploit that knowledge to improve performance in a target domain. A Note from the AI Magazine Editor in Chief: Part Two of the Structured Knowledge Transfer special issue will be published in the summer 2011 issue (volume 32 number 2) of AI Magazine. Articles in this issue will include: "Knowledge Transfer between Automated Planners," by Susana Fernández, Ricardo Aler, and Daniel Borrajo "Transfer Learning by Reusing Structured Knowledge," by Qiang Yang, Vincent W. Zheng, Bin Li, and Hankz Hankui Zhuo "An Application of Transfer to American Football: From Observation of Raw Video to Control in a Simulated Environment," by David J. Stracuzzi, Alan Fern, Kamal Ali, Robin Hess, Jervis Pinto, Nan Li, Tolga Könik, and Dan Shapiro "Toward a Computational Model of Transfer," by Daniel Oblinger While the field of psychology has studied transfer learning in people for many years, AI has only recently taken up the challenge. The topic received initial attention with work on inductive transfer in the 1990s, while the number of workshops and conferences has noticeably increased in the last five years. This special issue represents the state of the art in the subarea of transfer learning that focuses on the acquisition and reuse of structured knowledge.

The Defense Advanced Research Projects Agency (DARPA) explored the application of transfer -- a notion well studied in psychology -- to machine learning. This article discusses the formal measure of transfer and how it evolved. We discuss lessons learned, progress made at the formal and algorithmic levels, and thoughts about current and future prospects for the practical application of this technology. The aims of TLP were to understand and formally frame how this intuitively compelling psychological idea might apply in the computational context, build computational models of transfer learning (TL), and explore how these models might apply to practical learning tasks. TLP and the field as a whole made great strides in each of these dimensions.

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 Environments. The highlights of each symposium are presented in this report. The goal of the AAAI Fall Symposium on Advances in Cognitive Systems was to bring together researchers who are interested in developing intelligent systems that demonstrate the full range of human cognitive abilities and to report progress on this daunting task. The original aims of artificial intelligence, when it was launched in the late 1950s, were to explain intelligence in computational terms and to reproduce the entire range of human cognitive abilities in computational artifacts. Although the field has seen impressive advances in the last few decades, many researchers have, in the process, forgotten or abandoned these important goals. The purpose of the Fall Symposium on Advances in Cognitive Systems was to bring together scientists who remained committed to AI's original vision. The meeting received 50 paper submissions and it was attended by more than 75 participants, suggesting that there remains substantial interest in this view on the discipline. Research in cognitive systems, as reflected by the contributors to the meeting, differs from what has become mainstream AI in five basic ways.