The performance of online algorithms for learning dichotomies is studied. In online learning, the number of examples P is equivalent to the learning time, since each example is presented only once. The learning curve, or generalization error as a function of P, depends on the schedule at which the learning rate is lowered.

This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a flexible (and thus powerful) paradigm for teaching tasks because it allows an instructor to communicate whatever types of knowledge an agent might need in whatever situations might arise. To support this flexibility, however, the agent must be able to learn multiple kinds of knowledge from a broad range of instructional interactions. Our approach, called situated explanation, achieves such learning through a combination of analytic and inductive techniques. It combines a form of explanation-based learning that is situated for each instruction with a full suite of contextually guided responses to incomplete explanations. The approach is implemented in an agent called Instructo-Soar that learns hierarchies of new tasks and other domain knowledge from interactive natural language instructions. Instructo-Soar meets three key requirements of flexible instructability that distinguish it from previous systems: (1) it can take known or unknown commands at any instruction point; (2) it can handle instructions that apply to either its current situation or to a hypothetical situation specified in language (as in, for instance, conditional instructions); and (3) it can learn, from instructions, each class of knowledge it uses to perform tasks.

This report stems from a workshop that was organized by the Association for the Advancement of Artificial Intelligence (AAAI) and cosponsored by the Information Technology and Organizations Program of the National Science Foundation. The purpose of the workshop was twofold: first, to increase awareness among the artificial intelligence (AI) community of opportunities presented by the National Information Infrastructure (NII) activities, in particular, the Information Infrastructure and Tech-nology Applications (IITA) component of the High Performance Computing and Communications Program; and second, to identify key contributions of research in AI to the NII and IITA.

Several of the workshops have led to discourse? At what levels of the art in the field (Dale et al. 1992; generation is information processed on Natural Language Paris, Swartout, and Mann 1991; How can we generate to 24 June 1994 at the Nonantum The goal of this latest workshop multilingual texts efficiently? Inn on the seacoast in Kennebunkport, was to introduce new, cutting-edge The topics presented at the workshop Maine. Two invited speakers described subtopics such as evaluation, casual site contributed greatly to their perspectives on two areas outside explanation generation, and summarization the success of the workshop in stimulating the field that might become an occur with increasing frequency the exchange of ideas. Pustejovsky (Brandeis University) presented Different generator designers make that any individual generation his views on the richness of different choices, and the resulting project should define--in its own what can be encoded in what he calls systems are hard to compare.

Systems (QR '94) was held on 7-10 June A hot issue in cognitive modeling We received 53 submissions and is spatial and diagrammatic reasoning. The core issues of qualitative reasoning Hari Narayanan and his colleagues The eighth workshop was in Nara, included qualitative and (Advanced Research Laboratory, Japan, celebrating the community's causal modeling of the world, automated Hitachi Ltd.) exploited an architecture escape from a simple flip-flop behavior modeling, and qualitative of qualitative visual reasoning and its voyage to a more complex simulation. Interestingly, this transition attracted the attention of many participants. In fact, constructing a component-based sophistication to base qualitative several demonstrations, including model for the input-document handler reasoning on a firm ground. University) presented activity analysis, model abstraction that makes test Iwasaki and Farquhar and will be demonstrating how qualitative generation feasible for continuous held in Monterey, California.

The 1994 AAAI Robot-Building Laboratory (RBL-94) was held during the Twelfth National Conference on Artificial Intelligence. The primary goal of RBL-94 was to provide those with little or no robotics experience the opportunity to acquire practical experience in a few days. Thirty persons, with backgrounds ranging from university professors to practitioners from industry, participated in the three-part lab.

The Workshop on Using Knowledge in Its Context was held in Chambery, France, on 28 August 1993, preceding the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI-93). This article provides a summary of the discussions between the participants before (by e-mail) and during the one-day workshop. It is clear from these discussions that the notion of context is far from defined and is dependent in its interpretation on a cognitive science versus an engineering (or system building) point of view. In identifying the two points of view, this workshop permitted us to go one step further than previous workshops (notably Maskery and Meads [1992] and Maskery, Hopkins, and Dudley [1992]). Once a distinction is made on the viewpoint, one can achieve a surprising consensus on the aspects of context that the workshop addressed -- mainly, the position, the elements, the representation, and the use of context. Despite this consensus on the aspects of context, agreement on the definition of context was not yet achieved.

The general goal of this workshop was to bring t.ogether researchers working toward developing a theoretical framework for the analysis and design of neural networks. The t.echnical focus of the workshop was to address recent. The primary topics addressed the following three areas: 1) Computational complexity issues in neural networks, 2) Complexity issues in learning, and 3) Convergence and numerical properties of learning algorit.hms. Such st.udies, in t.urn, have generated considerable research interest. A similar development can be observed in t.he area of learning as well: Techniques primarily developed in the classical theory of learning are being applied to understand t.he generalization and learning characteristics of neural networks.

The general goal of this workshop was to bring t.ogether researchers working toward developing a theoretical framework for the analysis and design of neural networks. The t.echnical focus of the workshop was to address recent. The primary topics addressed the following three areas: 1) Computational complexityissues in neural networks, 2) Complexity issues in learning, and 3) Convergence and numerical properties of learning algorit.hms. Such st.udies, in t.urn, have generated considerable research interest. A similar development can be observed in t.he area of learning as well: Techniques primarily developed in the classical theory of learning are being applied to understand t.he generalization and learning characteristics of neural networks.

David A. Cohn MIT Dept. of Brain and Cognitive Sciences Cambridge, MA 02139 The goal of this workshop was to discuss two major issues: efficient exploration of a learner's state space, and learning in continuous domains. The common themes that emerged in presentations and in discussion were the importance of choosing one'sdomain assumptions carefully, mixing controllers/strategies, avoidance of catastrophic failure, new approaches with difficulties with reinforcement learning, and the importance of task transfer. He suggested that neither "fewer assumptions are better" nor "more assumptions are better" is a tenable position, and that we should strive to find and use standard sets of assumptions. With no such commonality, comparison of techniques and results is meaningless. Under Moore's guidance, the group discussed the possibility of designing an algorithm which used a number of well-chosen assumption sets and switched between them according to their empirical validity.