使用遗传算法的迷宫学习

本文试用遗传计算及决策制定方法来实现机器人有认识迷宫意向的能力，这里“意向”是指遵循对迷宫特有的路径规则所出的决定，令机器人在两个相对的迷宫中行走学习，一个迷宫路径是基于同样的意向，另一个则基于不同的意向，研究结果确认了已达成的意向学习。     

大规模数据库中的知识获取

一、前言数据是知识的潭泉,拥有大量的数据与拥有许多有用的知识完全是两回事.为了有效地利用大量的公共数据,必须更好地理解这些数据,并从其中快速、准确地发现知识.这里所说的知识是指大量数据中存在的规律性(r egularity)或不同属性值之间所存在的[I F THEN〕规则.将所获取的知识附加于仅由事实数据(fact data)构成的传统数据库上,既可强化数据库的查询能力,又可给数据库提供推理能力,     

人工关节试验机电液力伺服控制系统迭代学习控制策略仿真

本文首先介绍了人工关节试验机电液力伺服控制系统的构成，并分析了其静特性。针对力系统的特性，本文提出了一种闭环比例型一阶给定超前迭代学习控制算法，并对其控制效果进行了仿真研究。研究结果表明，采用迭代学习控制算法可以有效地提高力系统的跟随精度。     

空间机器人遥控、自主与协同操作的软件基础

空间机器人控制语言是实现空间机器人三种控制方式:遥控操作,自主操作和协同操作的软件基础,本文描述了该语言的基本结构,对于自主方式,给出了编程示例;对于遥控方式,运用程序辅助的方法,解决了操作员单独进行主/从操作时难以解决的问题.     

Design and Implementation of a Flexible Manufacturing Control System Using Neural Network

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elman's RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs.     

FILIP: A fuzzy intelligent information system with learning capabilities

FILIP (fuzzy intelligent learning information processing) system is designed with the goal to model human information processing. The issues addressed are uncertain knowledge representation and approximate reasoning based on fuzzy set theory, and knowledge acquisition by “being told” or by “learning from examples”. Concepts that can be “learned” by the system can be imprecise (fuzzy), or the knowledge can be incomplete. In the latter case, FILIP uses the concept of similarity to extrapolate the knowledge to cases that were not covered by examples provided by the user. Concepts are stored in the Knowledge Base and employed in intelligent query processing, based on flexible inference that supports approximate matches between the data in the database and the query.

The architecture of FILIP is discussed, the learning algorithm is described, and examples of the system's performance in the knowledge acquisition and querying modes, together with its explanatory capabilities are shown.     

Learning to Perceive and Act by Trial and Error

This article considers adaptive control architectures that integrate active sensory-motor systems with decision systems based on reinforcement learning. One unavoidable consequence of active perception is that the agent's internal representation often confounds external world states. We call this phoenomenon perceptual aliasingand show that it destabilizes existing reinforcement learning algorithms with respect to the optimal decision policy. We then describe a new decision system that overcomes these difficulties for a restricted class of decision problems. The system incorporates a perceptual subcycle within the overall decision cycle and uses a modified learning algorithm to suppress the effects of perceptual aliasing. The result is a control architecture that learns not only how to solve a task but also where to focus its visual attention in order to collect necessary sensory information.     

On the learning control of a robot manipulator

This paper derives a learning control law to achieve trajectory following for a robot manipulator. The controller consists of two parts, a computed torque servo for the rigid body terms that can be modelled and a learning law for the unmodelled dynamics. An advantage of this method is that bounds can be assigned to the position and velocity tracking errors.     

Learning to Predict Non-Deterministically Generated Strings

In this article we present an algorithm that learns to predict non-deterministically generated strings. The problem of learning to predict non-deterministically generated strings was raised by Dietterich and Michalski (1986). While their objective was to give heuristic techniques that could be used to rapidly and effectively learn to predict a somewhat limited class of strings, our objective is to give an algorithm which, though impractical, is capable of learning to predict a very general class. Our algorithm is meant to provide a general framework within which heuristic techniques can be effectively employed.     

Extending boosting for large scale spoken language understanding

We propose three methods for extending the Boosting family of classifiers motivated by the real-life problems we have encountered. First, we propose a semisupervised learning method for exploiting the unlabeled data in Boosting. We then present a novel classification model adaptation method. The goal of adaptation is optimizing an existing model for a new target application, which is similar to the previous one but may have different classes or class distributions. Finally, we present an efficient and effective cost-sensitive classification method that extends Boosting to allow for weighted classes. We evaluated these methods for call classification in the AT&;T VoiceTone^® spoken language understanding system. Our results indicate that it is possible to obtain the same classification performance by using 30% less labeled data when the unlabeled data is utilized through semisupervised learning. Using model adaptation we can achieve the same classification accuracy using less than half of the labeled data from the new application. Finally, we present significant improvements in the “important” (i.e., higher weighted) classes without a significant loss in overall performance using the proposed cost-sensitive classification method.