A common problem for companies with strong business growth is that it is hard to find enough experienced staff to support expansion needs. This problem is particular pronounced for operations planners and controllers who must be very highly knowledgeable and experienced with the business domain. This article is a case study of how one of the largest travel agencies in Hong Kong alleviated this problem by using AI to support decision-making and problem-solving so that their planners and controllers can work more effectively and efficiently to sustain business growth while maintaining consistent quality of service. AI is used in a mission critical fleet management system (FMS) that supports the scheduling and management of a fleet of luxury limousines for business travelers. The AI problem was modeled as a constraint satisfaction problem (CSP). The use of AI enabled the travel agency to sign up additional hotel partners, handle more orders and expand their fleet with their existing team of planners and controllers. Using modern web 2.0 architecture and proven AI technology, we were able to achieve low-risk implementation and deployment success with concrete and measurable business benefits.

A geoscientist would be faced with the situation shown on the right of the figure; his task is to deduce the situation shown at the left, along with the processes that were at work and the timeline involved. To accomplish this, a geoscientist first dates a set of rock samples from the present surface, then reasons backward to deduce what process affected the original landform. This is a difficult deduction: geological processes take place over an extremely long period of time, and evidence remaining today is scarce and noisy. Finally, experts in geological dating, like experts in any field, are only human, and can be biased in favor of one theory over another. In the face of these problems, experts form an exhaustive list of possible hypotheses and consider the evidence for and against each one--much like the AI concept of argumentation. Our system to automate this reasoning, Calvin, uses the same argumentation process as experts, comparing the strength of the evidence for and against a set of hypotheses before coming to a conclusion. We collected knowledge about how isotope dating experts reason through interviews with several dozen geoscientists.

In this article, we discuss the problem of transferring search heuristics from one planner to another. More specifically, we demonstrate how to transfer the domain-dependent heuristics acquired by one planner into a second planner. Our motivation is to improve the efficiency and the efficacy of the second planner by allowing it to use the transferred heuristics to capture domain regularities that it would not otherwise recognize. Our experimental results show that the transferred knowledge does improve the second planner's performance on novel tasks over a set of seven benchmark planning domains.

TLP and the field as a whole made great strides in each of these dimensions. Indeed, the program has helped TL become a recognized subdiscipline of machine learning. Other articles in this special issue detail the work accomplished in TLP; this article focuses on a broad framing of the research conducted and an assessment of its progress, limitations, and challenges, from an admittedly personal but DARPAinfluenced perspective. Traditionally every DARPA program has focused its research by requiring a precise measure of progress. The DARPA TLP decided to measure transfer by comparing the learning of tasks A and B versus the learning of B alone. In figure 1 the curve labeled B represents a traditional learning curve of the performance on target task B as a function of the number of training instances.

Transfer learning aims to solve new learning problems by extracting and making use of the common knowledge found in related domains. A key element of transfer learning is to identify structured knowledge to enable the knowledge transfer. Structured knowledge comes in different forms, depending on the nature of the learning problem and characteristics of the domains. In this article, we describe three of our recent works on transfer learning in a progressively more sophisticated order of the structured knowledge being transferred. We show that optimization methods, and techniques inspired by the concerns of data reuse can be applied to extract and transfer deep structural knowledge between a variety of source and target problems. In our examples, this knowledge spans explicit data labels, model parameters, relations between data clusters and relational action descriptions. 

The development of intelligent environments is considered the first and primary step toward the realization of the ambient intelligence vision and requires input from research and contributions from several scientific and engineering disciplines, including computer science, software engineering, artificial intelligence, architecture, social sciences, art, and design. IE conferences create a unique blend of researchers in these disciplines and foster crossdisciplinary discussions, debate, and collaborations. The Sixth International Conference on Intelligent Environments (IE 10) was held July 19-21 at the Sunway campus of Monash University, Kuala Lumpur, Malaysia. The general chairs were Simon Egerton of Monash University and Ichiro Satoh of the Japanese National Institute of Informatics. Vic Callaghan of the University of Essex, UK, and Achilles Kameas of the Hellenic Open University and Computer Technology Institute, Greece, served as program chairs.

We are proud to continue this tradition with the presentation of five articles from the Twenty Second IAAI conference that was held in Atlanta, Georgia, from July 11-14, 2010. We were especially honored to have Jay M. (Marty) Tenenbaum accept the Robert S. Engelmore Memorial Award for his exceptional contributions to AI in computer vision and manufacturing as well as his visionary role in the birth of electronic commerce. This issue of AI Magazine includes an article based on his lecture Cancer: A Computational Disease That AI Can Cure. In this article, Jay Tenenbaum and Jeff Shrager provide a personal view of their work in the development of an AIbased system that addresses the challenge of helping to find a cure for cancer. As a cancer survivor himself, Tenenbaum has a unique insight into the shortcomings of current approaches to treating this disease.

AIIDE 2010 was held October 11-13, 2010, at Stanford University ajacent to Palo Alto, California. The conference featured 17 paper presentations, 18 posters, 5 demos, 5 invited speakers, a panel on teaching game AI in academe, and the first StarCraft AI competition. Led by the conference chair, Michael Youngblood (University of North Carolina at Charlotte), and the program chair, Vadim Bulitko (University of Alberta), the three days of AIIDE contained a dense and exciting agenda highlighting new research and revealing how AI is applied in many commercial endeavors. The first day was kicked off with an invited talk from Chris Jurney, lead developer of Double Fine Productions, who detailed his work on the nonplayer character pathfinding of Dawn of War II during his time at Relic Entertainment. The morning was completed by research presentations on behavioral techniques with notable work on producing realistic behaviors through alibi generation (Ben Sunshine-Hill and Norman Badler, University of Pennsylvania), which has been widely discussed in the community since, and Ben Weber's (University of California, Santa Cruz) work applying goal-driven autonomy to playing StarCraft (awarded AIIDE 2010 Best Student Paper).

See Leuski et al. (2006) and to the same question -- for example, "What Leuski and Traum (2008) for more details. is your name?" -- depending on who the interactor The final parameter is the classification threshold is looking at. NPCEditor's user interface allows the on the KL-divergence value: only answers that designer to define arbitrary annotation classes or score above the threshold value are returned from categories and specify which of these annotation the classifier. The threshold is determined by tuning categories should be used in classification.

We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maximum likelihood is the most common approach to training CRFs, it ignores the inherent structure of the task's loss function. We describe alternatives to maximum likelihood which take that loss into account. These include a novel adaptation of a loss upper bound from the structured SVMs literature to the CRF context, as well as a new loss-inspired KL divergence objective which relies on the probabilistic nature of CRFs. These loss-sensitive objectives are compared to maximum likelihood using ranking as a benchmark task. This comparison confirms the importance of incorporating loss information in the probabilistic training of CRFs, with the loss-inspired KL outperforming all other objectives.