First, I would The editorial board members will play an active role in like to welcome B. Chandrasekaran, guiding the magazine, monitoring progress across the field of The Ohio and assuring that the magazine has timely, high-quality State University, as the articles on significant new developments. I expect the editorial new book review editor, board to have a considerable impact on the magazine, and Robert Morris, of and I am very grateful to the board members for NASA Ames Research Center, accepting this responsibility. I know that they will do an Finally, to expedite the processing of submissions, AI outstanding job, and I urge the AI community to actively Magazine will now accept submissions in electronic form. Full submission guidelines are available on the AI Magazine Chandrasekaran has prepared an editorial, appearing in home page, www.aaai.org/Magazine. I look forward to your this issue, presenting his vision for the book review section.

This year I had planned to nominate a even declining, the obvious conclusion worthy colleague as a AAAI fellow. Please note this that the number of Fellows Otherwise, the continuing nomination schedule shift in your calendars. The reasons have much significance, and AAAI's 1998, 4 Fellows; AAAI was significantly larger than it is they are, and to charter subcommittees It seems clear that there is little today. The program stated that the to propose solutions that could chance that my nomination will succeed total number of Fellows should number gain general approval. Of course the best solution would continued additions to their ranks.

A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from reasonably-sized training sets. Typically such bias is supplied by hand through the skill and insights of experts. In this paper a model for automatically learning bias is investigated. The central assumption of the model is that the learner is embedded within an environment of related learning tasks. Within such an environment the learner can sample from multiple tasks, and hence it can search for a hypothesis space that contains good solutions to many of the problems in the environment. Under certain restrictions on the set of all hypothesis spaces available to the learner, we show that a hypothesis space that performs well on a sufficiently large number of training tasks will also perform well when learning novel tasks in the same environment. Explicit bounds are also derived demonstrating that learning multiple tasks within an environment of related tasks can potentially give much better generalization than learning a single task.

We introduce a temporal model for reasoning on disjunctive metric constraints on intervals and time points in temporal contexts. This temporal model is composed of a labeled temporal algebra and its reasoning algorithms. The labeled temporal algebra defines labeled disjunctive metric point-based constraints, where each disjunct in each input disjunctive constraint is univocally associated to a label. Reasoning algorithms manage labeled constraints, associated label lists, and sets of mutually inconsistent disjuncts. These algorithms guarantee consistency and obtain a minimal network. Additionally, constraints can be organized in a hierarchy of alternative temporal contexts. Therefore, we can reason on context-dependent disjunctive metric constraints on intervals and points. Moreover, the model is able to represent non-binary constraints, such that logical dependencies on disjuncts in constraints can be handled. The computational cost of reasoning algorithms is exponential in accordance with the underlying problem complexity, although some improvements are proposed.

This paper reviews the connections between Graphplan's planning-graph and the dynamic constraint satisfaction problem and motivates the need for adapting CSP search techniques to the Graphplan algorithm. It then describes how explanation based learning, dependency directed backtracking, dynamic variable ordering, forward checking, sticky values and random-restart search strategies can be adapted to Graphplan. Empirical results are provided to demonstrate that these augmentations improve Graphplan's performance significantly (up to 1000x speedups) on several benchmark problems. Special attention is paid to the explanation-based learning and dependency directed backtracking techniques as they are empirically found to be most useful in improving the performance of Graphplan.

We show the similarity between belief propagation and TAP, for decoding corrupted messages encoded by Sourlas's method.

A nonlinear modification to PI control is motivated by a model of a signal transduction pathway active in mammalian blood pressure regulation.This control algorithm, labeled PII (proportional with intermittent integral), is appropriate for plants requiring exact set-pointmatching and disturbance attenuation in the presence of infrequent step changes in load disturbances or set-point. The proportional aspect of the controller is independently designed to be a disturbance attenuator and set-point matching is achieved by intermittently invoking an integral controller. The mechanisms observed in the Angiotensin 11/AT1 signaling pathway are used to control the switching of the integral control. Improved performance over PI control is shown on a model of cyc1opentenol production. A sign change in plant gain at the desirable operating point causes traditional PI control to result in an unstable system.

We show the similarity between belief propagation and TAP, for decoding corrupted messages encoded by Sourlas's method.

A nonlinear modification to PI control is motivated by a model of a signal transduction pathway active in mammalian blood pressure regulation. This control algorithm, labeled PII (proportional with intermittent integral), is appropriate for plants requiring exact set-point matching and disturbance attenuation in the presence of infrequent step changes in load disturbances or set-point. The proportional aspect of the controller is independently designed to be a disturbance attenuator and set-point matching is achieved by intermittently invoking an integral controller. The mechanisms observed in the Angiotensin 11/ AT1 signaling pathway are used to control the switching of the integral control. Improved performance over PI control is shown on a model of cyc1opentenol production. A sign change in plant gain at the desirable operating point causes traditional PI control to result in an unstable system.

We show the similarity between belief propagation and TAP, for decoding corrupted messages encoded by Sourlas's method.