Learning Automata from Ordered Examples

Connectionist learning models have had considerable empirical success, but it is hard to characterize exactly what they learn. The learning of finite-state languages (FSL) from example strings is a domain which has been extensively studied and might provide an opportunity to help understand connectionist learning. A major problem is that traditional FSL learning assumes the storage of all examples and thus violates connectionist principles. This paper presents a provably correct algorithm for inferring any minimum-state deterministic finite-state automata (FSA) from a complete ordered sample using limited total storage and without storing example strings. The algorithm is an iterative strategy that uses at each stage a current encoding of the data considered so far, and one single sample string. One of the crucial advantages of our algorithm is that the total amount of space used in the course of learning for encoding any finite prefix of the sample is polynomial in the size of the inferred minimum state deterministic FSA. The algorithm is also relatively efficient in time and has been implemented. More importantly, there is a connectionist version of the algorithm that preserves these properties. The connectionist version requires much more structure than the usual models and has been implemented using the Rochester Connectionist Simulator. We also show that no machine with finite working storage can iteratively identify the FSL from arbitrary presentations.     

Generation and selection of likely interpretations during plan recognition in task-oriented consultation systems

This paper presents a mechanism which infers a user's plans from his/her utterances by directing the inference process towards the more likely interpretations of a speaker's statements among many possible interpretations. Our mechanism uses Bayesian theory of probability to assess the likelihood of an interpretation, and it complements this assessment by taking into consideration two aspects of an interpretation: its coherence and its information content. The coherence of an interpretation is determined by the relationships between the different statements in the discourse. The information content of an interpretation is a measure of how well defined the interpretation is in terms of the actions to be performed on the basis of this interpretation. This measure is used to guide the inference process towards interpretations with higher information content. The information content of an interpretation depends on the specificity and the certainty of the inferences in it, where the certainty of an inference depends on the knowledge on which the inference is based. Our mechanism has been developed for use in task-oriented consultation systems. The particular domain that we have chosen for exploration is that of travel booking.     

Why is science difficult to learn? Things are seldom what they seem

Abstract The difficulties of learning science are related to the nature of science itself and to the methods by which science is customarily taught without regard to what is known about children's learning. An information processing model is proposed to guide thinking and research in this area.     

Pruning Algorithms for Rule Learning

Pre-pruning and Post-pruning are two standard techniques for handling noise in decision tree learning. Pre-pruning deals with noise during learning, while post-pruning addresses this problem after an overfitting theory has been learned. We first review several adaptations of pre- and post-pruning techniques for separate-and-conquer rule learning algorithms and discuss some fundamental problems. The primary goal of this paper is to show how to solve these problems with two new algorithms that combine and integrate pre- and post-pruning.     

美籍华裔专家讲通信工程技术新动态

本文扼要介绍１９９５年北京中美工程技术研讨会通信组五位美籍华裔专家关于通信技术新动态的专题报告。一是宽带综合业务数字网的同步数字系列（ＳＤＨ）和异步转移模式（ＡＴＭ）；二是光纤通信系统的光放大器（ＯＦＡ）、波分多路（ＷＤＭ）、光电子集成（ＯＥＩＣ）、色散补偿和新型光纤；三是蜂窝网车载移动通信和全国性个人通信业务（ＰＣＳ）、时分多址（ＴＤＭＡ）和码分多址（ＣＤＭＡ），四是智能网（ＩＮ）体系结构、概念模型和业务管理系统（ＳＭＳ）；五是数字传输网的恢复（ＦＡＳＴＡＲ）、维护（ＴＭＰ）和供应（ＴＳＮＯＷ）三种管理平台，及综合网络管理系统（ＩＮＭＳ）。     

SMS——智能网的业务管理系统

本文叙述了智能网的业务管理系统所实现的３种功能：业务管理功能，网络管理功能和业务管理访问功能，还介绍了业务管理和网络管理之间的关系，ＳＭＳ的集中式和分布式两种体系结构及业务管理功能的设计方法和进一步研究方向。     

微机字处理网络系统智能接口的设计

本文介绍了微机字处理系统网络联机的智能接口设计方案，采用比较简单而独特的手法，解决了通信控制和资源共享问题．     

智能压力传感器

讨论了压阻式智能传感器的设计,并以80C31单片机为核心构成了一个能检测压力、温度的智能传感器,它能实现量程的自动变换、故障的自诊断及数据的处理,通过软件实现了对半导体传感器的零点修正、非线性修正及温度补偿。实验表明,传感器的智能化改善了传感器的性能。     

Law,liability and expert systems

This paper examines some of the possible legal implications of the production, marketing and use of expert systems. The relevance of a legally useful definition of expert systems, comprising systems designed for use both by laymen and professionals, is related to the distinctions inherent in the legal doctrine underlying provision of goods and provision of services. The liability of the sellers and users of, and contributors to, expert systems are examined in terms of professional malpractice as well as product liability. A recurring theme indicates that legislators may be inclined to restrict possibilities of liability suits in order to avoid disincentives to the creation of expert systems.