Sequential decision tasks present many opportunities for the study of transfer learning. A principal one among them is the existence of multiple domains that share the same underlying causal structure for actions. We describe an approach that exploits this shared causal structure to discover a hierarchical task structure in a source domain, which in turn speeds up learning of task execution knowledge in a new target domain. Our approach is theoretically justified and compares favorably to manually designed task hierarchies in learning efficiency in the target domain. We demonstrate that causally motivated task hierarchies transfer more robustly than other kinds of detailed knowledge that depend on the idiosyncrasies of the source domain and are hence less transferable.

This project describes the electricity demand and energy consumption management system and its application to Southern Peru smelter. It is composed of an hourly demand-forecasting module and of a simulation component for a plant electrical system. The first module was done using dynamic neural networks with backpropagation training algorithm; it is used to predict the electric power demanded every hour, with an error percentage below of 1%. This information allows efficient management of energy peak demands before this happen, distributing the raise of electric load to other hours or improving those equipments that increase the demand. The simulation module is based in advanced estimation techniques, such as: parametric estimation, neural network modeling, statistic regression and previously developed models, which simulates the electric behavior of the smelter plant. These modules facilitate electricity demand and consumption proper planning, because they allow knowing the behavior of the hourly demand and the consumption patterns of the plant, including the bill components, but also energy deficiencies and opportunities for improvement, based on analysis of information about equipments, processes and production plans, as well as maintenance programs. Finally the results of its application in Southern Peru smelter are presented.

New this year: Attendance at the tutorials is May 20, 2011.

David McAllester and David Rosenblitt's paper, "Systematic Nonlinear Planning" (published This commentary by Daniel S. Weld describes David Rosenblitt's paper, "Systematic Nonlinear Planning" (McAllester and Rosenblitt 1991), presented 19 years ago at the Ninth National Conference on Artificial Intelligence (AAAI-91), had two major impacts on the field: (1) an elegant algorithm and (2) endorsement of the lifting technique. The paper's biggest impact stems from its extremely clear and simple presentation of a sound and complete algorithm (known as SNLP or POP) for classical planning. While it is easy to define such an algorithm as search through the space of world states, SNLP is a "partialorder" planner, meaning it searches the space of partially specified plans, where only partial constraints on action arguments and ordering decisions are maintained. Here, McAllester and Rosenblitt benefited from David Chapman's elegant TWEAK planner, which greatly clarified previous partial-order algorithms (Chapman 1985). SNLP's key feature is the use of a data structure, called a causal link, to record the planner's commitment to establish a precondition of one action with the postcondition of another.

The Association for the Advancement of Artificial Intelligence was pleased to present the 2010 Fall Symposium Series, held Thursday through Saturday, November 11-13, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the eight symposia are as follows: (1) Cognitive and Metacognitive Educational Systems; (2) Commonsense Knowledge; (3) Complex Adaptive Systems: Resilience, Robustness, and Evolvability; (4) Computational Models of Narrative; (5) Dialog with Robots; (6) Manifold Learning and Its Applications; (7) Proactive Assistant Agents ; and (8) Quantum Informatics for Cognitive, Social, and Semantic Processes. The highlights of each symposium are presented in this report.

EAAI encourages the sharing of innovative educational approaches that convey or leverage AI and its many subfields, including robotics, machine learning, natural language, and computer vision. EAAI follows the successful 2008 Spring Symposium on "Using AI to Motivate Greater Participation in Computer Science" and the 2008 AAAI AI Education Colloquium. Fifty-five attendees formally registered for the event, but many other AAAI attendees also visited one or more EAAI events. EAAI is planned to become an annual event; EAAI-11 will be held in San Francisco on August 9-10, 2011, collocated with AAAI-11. The 2010 symposium included an invited talk, paper presentations, model AI assignments, a teaching and mentoring workshop, a best educational video award, and a robotics track.

For example, baby boomers are aging. Researchers are actively pursuing interdisciplinary research that enables robots to function autnomously within arbitrary environments alongside people. The goal of the AAAI 2010 Workshop on Enabling Intelligence through Middleware was to examine both the successes and opportunities to provide tools that enable a larger pool of researchers to experiment with embodied, intelligent algorithms. The half-day workshop, attended by over 80 people, was held as part of the Twenty-Fourth AAAI Conference on Artificial Intelligence in Atlanta Georgia on July 12, 2010. The workshop consisted of two parts: (1) invited talks and (2) middleware presentations.

We have explored the use of analogy as a general approach to near and far transfer learning in domains ranging from physics problem solving to strategy games (Klenk and Forbus 2007; Hinrichs and Forbus 2007). Using the same basic analogical mechanism, we have found that the main differences between near and far transfer involve the amount of generalization that must be performed prior to transfer and the way that the matching process treats nonidentical predicates. We present here two extensions of our analogical matcher, minimal ascension and metamapping, that enable far transfer between representations with different relational vocabulary. Evidence for the effectiveness of these techniques is provided by a large-scale external evaluation, involving a substantial number of novel distant analogs.

Case-based reasoning (CBR) is a problem-solving process in which a new problem is solved by retrieving a similar situation and reusing its solution. Transfer learning occurs when, after gaining experience from learning how to solve source problems, the same learner exploits this experience to improve performance and/or learning on target problems. In transfer learning, the differences between the source and target problems characterize the transfer distance. CBR can support transfer learning methods in multiple ways. We illustrate how CBR and transfer learning interact and characterize three approaches for using CBR in transfer learning: (1) as a transfer learning method, (2) for problem learning, and (3) to transfer knowledge between sets of problems. We describe examples of these approaches from our own and related work and discuss applicable transfer distances for each. We close with conclusions and directions for future research applying CBR to transfer learning.

This article argues that currently the largest gap between human and machine learning is learning algorithms' inability to perform deep transfer, that is, generalize from one domain to another domain containing different objects, classes, properties and relations. We argue that second-order Markov logic is ideally suited for this purpose, and propose an approach based on it. Our algorithm discovers structural regularities in the source domain in the form of Markov logic formulas with predicate variables, and instantiates these formulas with predicates from the target domain. Our approach has successfully transferred learned knowledge among molecular biology, Web and social network domains.