People regularly use objects in the environment as tools to achieve their goals. In this paper we report extensions to the ICARUS cognitive architecture that let it create and use combinations of objects inthis manner. These extensions include the ability to represent virtual objects composed of simpler ones and to reason about their quantitative features. They also include revised modules for planning and execution that operate over this hybrid representation, taking into account both relational structures and numeric attributes. We demonstrate the extended architecture's behavior on a number of tasks that involve tool construction and use, after which we discuss related research and plans for future work.

This includes memory stores and the representations of elements in those memories, but not their contents, Most research in AI is analytic, in that it selects some facet which change as the result of external stimuli and internal of intelligence and attempts to understand it in detail, typically processing. In this sense, a cognitive architecture is analogous in isolation from other elements. This is balanced by to a building architecture, which describes its fixed a smaller movement, synthetic in character, that aims to discover structure (e.g., floors, rooms, and doors), but not its replaceable how different aspects of intelligence interact.

Inductive process modeling involves the construction of explanatory accounts for multivariate time series. As typically specified, background knowledge is available in the form of generic processes that serve as the building blocks for candidate model structures. In this paper, we present a more flexible approach that, when available processes are insufficient to construct an acceptable model, automatically produces new generic processes that let it complete the task. We describe FPM, a system that implements this idea by composing knowledge about algebraic rate expressions and about conceptual processes like predation and remineralization in ecology. We demonstrate empirically FPM's ability to construct new generic processes when necessary and to transfer them later to new modeling tasks. We also compare its failure-driven approach with a naive scheme that generates all possible processes at the outset. We conclude by discussing prior work on equation discovery and model construction, along with plans for additional research.

Scientists use two forms of knowledge in the construction ofexplanatory models: generalized entities and processes that relatethem; and constraints that specify acceptable combinations of thesecomponents. Previous research on inductive process modeling, whichconstructs models from knowledge and time-series data, has relied onhandcrafted constraints. In this paper, we report an approach todiscovering such constraints from a set of models that have beenranked according to their error on observations. Our approach adaptsinductive techniques for supervised learning to identify processcombinations that characterize accurate models. We evaluate themethod's ability to reconstruct known constraints and to generalizewell to other modeling tasks in the same domain. Experiments with synthetic data indicate that the approach can successfully reconstructknown modeling constraints. Another study using natural data suggests that transferring constraints acquired from one modeling scenario to another within the same domain considerably reduces the amount of search for candidate model structures while retaining the most accurate ones.

Every year, AI Magazine devotes one fourth of its annual production to a special issue based on the Innovative Applications of Artificial Intelligence conference. Because IAAI is the premier venue for documenting the transition of AI technology into application, these special issues provide a snapshot of the state of the art in AI with the practical syllogism in mind; they present work that has value because it delivers value in use.

As a result, it is good to read these articles from a practical perspective. Papers that document deployed systems clarify the motivating application constraints, the match (and mismatch) between problems and technology, the innovations required to surmount barriers to deployment, and the impact of technology on application through practical measures of cost and benefit. Other articles describe applications that are almost feasible, drawn from papers in the IAAI emergent applications track. These papers provide a window into the search for viable applications at an earlier stage in the process of mating task with technology. All of the articles supply insight into the core question of what is feasible and why, which is a useful lens for us, as readers, to employ in viewing our own work. This special issue of AI Magazine contains expanded versions of five papers that describe deployed applications and two papers that discuss emergent applications from IAAI-11 (the article by Warrick and colleagues is from IAAI-10).

This paper proposes a novel agenda for cognitive systems research focused on the "social agency" problem, which concerns acting to produce mental states in other agents in addition to physical states of the world. The capacity for social agency will enable agents to perform a wide array of tasks in close association with people and is a valuable first step towards broader social cognition. We argue that existing cognitive systems have not addressed social agency because they lack a number of the required mechanisms. We describe an initial approach set in a toy scenario based on capabilities native to the ICARUS cognitive architecture. We utilize an analysis of this approach to highlight the open issues required for social agency and to encourage other researchers to address this important problem.

This issue of AI Magazine provides extended versions of several papers that were recently presented at the Innovative Applications of Artificial Intelligence Conference (IAAI-2010). We present three articles reflecting deployed applications of AI, one describing a unique, emerging application, plus an article based on the invited talk by Jay M. Tenenbaum, who was the 2010 Engelmore Award recipient.

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.

Automatic transfer of learned knowledge from one task or domain to another offers great potential to simplify and expedite the construction and deployment of intelligent systems. In practice however, there are many barriers to achieving this goal. In this article, we present a prototype system for the real-world context of transferring knowledge of American football from video observation to control in a game simulator. We trace an example play from the raw video through execution and adaptation in the simulator, highlighting the system's component algorithms along with issues of complexity, generality, and scale. We then conclude with a discussion of the implications of this work for other applications, along with several possible improvements.