The SciFinance software synthesis system, licensed to major investment banks, automates programming for financial risk-management activities -- from algorithms research to production pricing to risk control. SciFinance's high-level, extensible specification language, aspen, lets quantitative analysts generate code from concise model descriptions written in application-specific and mathematical terminology; typically, a page or less produces thousands of lines of c. aspen's abstractions help analysts focus on their primary tasks -- model description, validation, and analysis -- rather than on programming details. Compared with manual programming, automation produces codes that are more sophisticated, accurate, and consistent. Analysts develop models within a day that previously took weeks or were not even attempted. SciFinance extends a system that generates scientific computing codes in a variety of target languages. The implementation integrates an object-oriented knowledge base, refinement and optimization rules, computer algebra, and a planning system. The shared knowledge base is used by the specification checker, synthesis system, and information portal.

A few weeks after my appointment as Book Reviews editor, I started receiving a large number of books from AAAI, books that have been accumulating since the last reviewer stepped down. As I was going through them, I thought, "So many books, so few pages." AI Magazine is not a publication exclusively devoted to books, such as the New York Review or the weekly book review supplements of major newspapers. At best, it can devote a few pages each issue to book reviews. Also, it doesn't appear that frequently, just four issues a year. Given these constraints, how can the magazine best serve its readership?

This article discusses five years of experience using three international mobile robot competitions as the foundation for educational projects in undergraduate and graduate computer science courses. The three competitions -- (1) AAAI Mobile Robot, (2) AUVS Unmanned Ground Robotics, and (3) IJCAI RoboCup -- were used in different years for an introductory undergraduate robotics course, an advanced graduate robotics course, and an undergraduate practicum course. Based on these experiences, a strategy is presented for incorporating competitions into courses in such a way as to foster intellectual maturation as well as learn lessons in organizing courses and fielding teams. The article also provides a classification of the major robot competitions and discusses the relative merits of each for educational projects, including the expected course level of computer science students, equipment needed, and costs.

Calculation of Q(t) and R(t) using (4, 5, 7, 9) to execute the path average and the average over sets is relatively straightforward, albeit tedious. We find that -"Yt(l -"Yt)

Calculation of Q(t) and R(t) using (4, 5, 7, 9) to execute the path average and the average over sets is relatively straightforward, albeit tedious. We find that -"Yt(l -"Yt)

Calculation of Q(t) and R(t) using (4, 5, 7, 9) to execute the path average and the average over sets is relatively straightforward, albeit tedious. We find that -"Yt(l -"Yt)

To not only proving new mathematical obtain broader input, especially from countries results by computer but also formally verifying outside North America, a call for commentaries the correctness of (certain properties of) computer was issued to the automated deduction community.

An adaptive online algorithm is proposed to estimate hierarchical data structures for non-stationary data sources. The approach is based on the principle of minimum cross entropy to derive a decision tree for data clustering and it employs a metalearning idea (learning to learn) to adapt to changes in data characteristics. Its efficiency is demonstrated by grouping non-stationary artifical data and by hierarchical segmentation of LANDSAT images. 1 Introduction Unsupervised learning addresses the problem to detect structure inherent in unlabeled and unclassified data. N. The encoding usually is represented by an assignment matrix M (Mia), where Mia 1 if and only if Xi belongs to cluster L: 1 MiaV (Xi, Ya) measures the quality of a data partition, Le., optimal assignments and prototypes (M,y)OPt argminM,y1i (M,Y) minimize the inhomogeneity of clusters w.r.t. a given distance measure V. For reasons of simplicity we restrict the presentation to the ' sum-of-squared-error criterion V(x, y) To facilitate this minimization a deterministic annealing approach was proposed in [5] signments, which maps the discrete optimization problem, i.e. how to determine the data as via the Maximum Entropy Principle [2] to a continuous parameter es- Unsupervised Online Learning of Decision Trees for Data Analysis 515 timation problem.

Singular value decomposition (SVD) can be viewed as a method for unsupervised training of a network that associates two classes of events reciprocally by linear connections through a single hidden layer. SVD was used to learn and represent relations among very large numbers of words (20k-60k) and very large numbers of natural text passages (lk-70k) in which they occurred. The result was 100-350 dimensional "semantic spaces" in which any trained or newly aibl word or passage could be represented as a vector, and similarities were measured by the cosine of the contained angle between vectors. Good accmacy in simulating human judgments and behaviors has been demonstrated by performance on multiple-choice vocabulary and domain knowledge tests, emulation of expert essay evaluations, and in several other ways. Examples are also given of how the kind of knowledge extracted by this method can be applied.

We present a method for determining the globally optimal online learning rule for a soft committee machine under a statistical mechanics framework. This work complements previous results on locally optimal rules, where only the rate of change in generalization error was considered. We maximize the total reduction in generalization error over the whole learning process and show how the resulting rule can significantly outperform the locally optimal rule. 1 Introduction We consider a learning scenario in which a feed-forward neural network model (the student) emulates an unknown mapping (the teacher), given a set of training examples produced by the teacher. The performance of the student network is typically measured by its generalization error, which is the expected error on an unseen example. The aim of training is to reduce the generalization error by adapting the student network's parameters appropriately. A common form of training is online learning, where training patterns are presented sequentially and independently to the network at each learning step.