神经网络系统学习过程初探

本文给出了神经网络系统学习过程的一个随机模型--马尔柯夫模型,从最大熵原理的 观点讨论神经网络系统的学习过程,提出将神经网络系统的学习过程分为两个阶段的想法并 给出学习过程的算法.     

Visual thinking in arts education: Homage to Rudolf Arnheim.

The influence of Arnheim's work on the author's research began with an experiment on the perception of visual balance. Two later research projects emerged from the profound influence of Arnheim's stance toward creation in the visual arts as a serious, cognitive endeavor. A series of meta-analyses were first conducted to test the claim that learning in the arts transfers to nonarts cognitive domains, but little evidence was found. Past research on the transfer hypothesis was found to be lacking because of its failure to assess learning in the parent domain. Therefore, a new research project was carried out to identify kinds of learning in the parent domain of visual arts. We identified eight thinking dispositions developed in serious visual arts classes, setting the stage for more plausible transfer studies. This study demonstrates that the visual arts inculcate basic skills in perception and cognition that exist both in the arts and sciences. All of the skills the authors describe can, with some modification, be transferred to the science laboratory. As Rudolf Arnheim has taught us, visual thinking is everywhere. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Confucian and Socratic learning.

Replies to the comments by R. A. R. Gurung (see record 2003-03405-011) and J. Li (see record 2003-03405-012) regarding comments on the article by R. G. Tweed and D. R. Lehman (2001) which stated that a Confucian-Socratic framework provides a structure for analyzing culture-influenced aspects of academic learning. In this article, Tweed and Lehman argued that these ancient exemplars model approaches to learning continue to differentiate students within a modern Canadian postsecondary context. In this reply, Tweed and Lehman advise caution in how Gurung placed their Confucian-Socratic framework within the context of prior theory on education and epistemological development because these models were developed exclusively in the West. Furthermore, Tweed and Lehman believe that Li's argument misinterpreted their article, and that they should of consistently used the term "personal reform" rather than "behavioral reform" in order to communicate the depth of personal change envisioned by Confucius. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

What do we learn from binding features? Evidence for multilevel feature integration.

Four experiments were conducted to investigate the relationship between the binding of visual features (as measured by their aftereffects on subsequent binding) and the learning of feature-conjunction probabilities. Both binding and learning effects were obtained, but they did not interact. Interestingly, (shape-color) binding effects disappeared with increasing practice, presumably because of the fact that only 1 of the features involved was relevant to the task. However, this instability was only observed for arbitrary, not highly overlearned combinations of simple geometric features and not for real objects (colored pictures of a banana and strawberry), where binding effects were strong and resistant to practice. These findings suggest that learning has no direct impact on the strength or resistance of bindings or on speed with which features are bound; however, learning does affect the amount of attention particular feature dimensions attract, which again can influence which features are considered in binding. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

The Design of Discrimination Experiments

Experimentation plays a fundamental role in scientific discovery. Scientists experiment to gather data, investigate phenomena, measure quantities, and test theories. In this article, we address the problem of designing experiments to discriminate between two completing theories. Given an initial situation for which the two theories make the same prediction, the experiment design problem is to determine how to modify the situation such that the two theories make different predictions for the modified situation. The modified situation is called a discrimination experiment. We present a knowledge-intensive method called DEED for designing discrimination experiments. The method analyzes the differences in the two theories' explanations of the prediction for the initial situation. Based on this analysis, it determines modifications to the initial situation that will result in a discrimination experiment. We illustrate the method with the design of experiments to discriminate between several pairs of qualitative theories in the fluids domain.     

A machine learning system for identifying transmembrane domains from amino acid sequences

We present our machine learning system, that uses inductive logic programming techniques to learn how to identify transmembrane domains from amino acid sequences. Our system facilitates the use of operators such as ‘contains’, that act on entire sequences, rather than on individual elements of a sequence. The prediction accuracy of our new system is around 93%, and this compares favourably with earlier results. This work was carried out with the support of a research grant from ISIS, Fujitsu Laboratories.     

光刻胶灰化工艺与深亚微米线条的制作

随着器件尺寸的缩小，细线条的制作成为很关键的工艺，普通光学光刻已接近其分辨率的极限，而电子束光刻和Ｘ射线光刻技术复杂、费用昂贵。本文对光刻胶灰化工艺进行了分析和研究，并应用此工艺进行了深亚微米线条的制作，在普通光学光刻机上制作出宽度小于０．２５μｍ细线条。我们已将此工艺成功地应用在深亚微米ＭＯＳＦＥＴ的制作中。     

MKR──一种有效的增量式概念获取系统

本文对示例式学习的ＩＤ５Ｒ算法进行了深入的研究并作了进一步的改进，提高了其计算效率．并提出一种适合于增量式学习的抗干扰机制，拓广了算法的适用范围．     

用奇异模型描述的受限机器人的学习控制

本文了一类受限机器人的迭代学习控制方案，控制器的设计是基于机器人模型的降阶形式。在存在有界未知干扰的情况下，对末端操纵器受线性、无摩擦约束面的受限机器人。本文给出的控制方案保证了机器人系统的完全运动跟踪，同时保证了力跟踪误差有界的，且界的大小是可调节的。     

Real-World Robotics: Learning to Plan for Robust Execution

In executing classical plans in the real world, small discrepancies between a planner's internal representations and the real world are unavoidable. These can conspire to cause real-world failures even though the planner is sound and, therefore, proves that a sequence of actions achieves the goal. Permissive planning, a machine learning extension to classical planning, is one response to this difficulty. This paper describes the permissive planning approach and presents GRASPER, a permissive planning robotic system that learns to robustly pick up novel objects.