Plotting

 Overview


An experimental comparison of recurrent neural networks

Neural Information Processing Systems

Many different discrete-time recurrent neural network architectures have been proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.


Active Learning with Statistical Models

Neural Information Processing Systems

For many types of learners one can compute the statistically "optimal" way to select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992; Cohn, 1994]. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.


The Innovative Applications Conference Highlights and Changes

AI Magazine

Daewoo Heavy Industries, in conjunction with the Korean Advanced Institute of Science and Technology, integrated applicability and limitations of various five separate schedulers based on different several papers from the AI techniques. IAAI has been held annually that are addressed at the conference. Mita Industrial Co., Ltd., said Japan's troubleshooting expert system proceedings were published in book Seventeen applications represent this has been supplied as an embedded form through 1992. Since 1993, a year's award winners: 11 were from component of its photocopiers conference proceedings volume has the United States, 4 from the Pacific since April 1994. It uses new reasoning been published, and selected papers Rim, 1 from Europe, and 1 from the methods based on virtual cases have been republished as articles in Middle East.



Intelligent Agents for Interactive Simulation Environments

AI Magazine

Interactive simulation environments constitute one of today's promising emerging technologies, with applications in areas such as education, manufacturing, entertainment, and training. These environments are also rich domains for building and investigating intelligent automated agents, with requirements for the integration of a variety of agent capabilities but without the costs and demands of low-level perceptual processing or robotic control. Our current target is intelligent automated pilots for battlefield-simulation environments. This article provides an overview of this domain and project by analyzing the challenges that automated pilots face in battlefield simulations, describing how TacAir-Soar is successfully able to address many of them -- TacAir-Soar pilots have already successfully participated in constrained air-combat simulations against expert human pilots -- and discussing the issues involved in resolving the remaining research challenges.


Decoding Cursive Scripts

Neural Information Processing Systems

Online cursive handwriting recognition is currently one of the most intriguing challenges in pattern recognition. This study presents a novel approach to this problem which is composed of two complementary phases.The first is dynamic encoding of the writing trajectory into a compact sequence of discrete motor control symbols. In this compact representation we largely remove the redundancy of the script, while preserving most of its intelligible components. In the second phase these control sequences are used to train adaptive probabilistic acyclic automata (PAA) for the important ingredients of the writing trajectories, e.g.


Decoding Cursive Scripts

Neural Information Processing Systems

Online cursive handwriting recognition is currently one of the most intriguing challenges in pattern recognition. This study presents a novel approach to this problem which is composed of two complementary phases. The first is dynamic encoding of the writing trajectory into a compact sequence of discrete motor control symbols. In this compact representation we largely remove the redundancy of the script, while preserving most of its intelligible components. In the second phase these control sequences are used to train adaptive probabilistic acyclic automata (PAA) for the important ingredients of the writing trajectories, e.g.