ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00346.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

Abstract:Knowledge based systems offer considerable potential for the creation of new learning environments. In education such environments can be used with the mediation of a teacher and limits to the interpretation of the knowledge do not necessarily present problems. Intelligent tutoring systems cannot rely on human mediation and all interpretation of learner understanding is restricted to semantics of the knowledge representation. Thus the choice of representation is fundamental to the design of an intelligent tutoring system. Experience from an engineering context suggests that the success of a few intelligent tutoring systems depends on the formal nature of the topics considered. Typical topics for education and training require the integration of a formal understanding with an informal interpretation of considerable complexity. A new approach to the use of knowledge based systems, firmly centred on experience of applications actively used in education and/or training, will be required to solve this problem.

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00347.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

Abstract:The Trainee Teacher Support System (TTSS) is a computer based advisory system for trainee teachers. Development work, in the form of a feasibility study, has been conducted over the past three years. The main purpose of this study is to investigate the application of expert systems technology and artificial intelligence techniques to the formalisation of experienced teachers’ knowledge of classroom practice. The domain chosen is that of the school based ‘teacher‐tutor’, responsible for guiding and advising the trainee teacher. The TTSS embodies a model of processes which underly classroom events. It has a knowledge base of rules, accumulates a database of facts and has a rule implementation program. It is undergoing continued development in order to capture the teacher‐tutor's understanding of classroom dynamics on a finer

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00348.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

Abstract:The domain of mathematics has played a special part in the evolution of Intelligent Tutoring Systems (ITSs), beginning as far back as the 1950s when conventional Computer Assisted Instruction (CAI) came into being. A brief historical review of this evolutionary process is presented, followed by a selective survey of some of the intelligent tutoring systems in the mathematics domain as well as some of their shortcomings and the criticisms levelled against them. The work achieved so far towards the realisation of an intelligent tutoring system for a complex mathematical domain is presented. A major conclusion is that the ‘mal‐rule’ methodology for developing tutoring systems may lend itself to simple ‘primitive’ domains, but its credibility is seriously questioned when it is applied to more ‘complex’ domains. An alternative methodology is proposed to solve this problem, together with an

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00349.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

Abstract:The article summarises the results of a five year research programme aimed at the creation and development of a prototype ‘intelligent authoring system’(IAS)—that is. a system for authoring software that stimulates the skills and knowledge of a conventional Computer Assisted Learning authoring team, thus allowing a computer‐naive author to create a working program interactively without the need for human assistance. We argue that a knowledge representation in the form of ‘event schema’ or 'script’ for each of the common types of educational software is ideally suited to meeting our five main criteria for IAS development, and present a brief of overview of the SCALD’(Scriptal CAL Designer) prototype IAS. The current version of the system is implemented in Prolog on an Apple Macintosh micro, and is capable of creating a range of educational programs of either ‘an instructional’ type or a 'science demonstration’ type. We believe that scripts could be produced fairly easily for most other types of program design and are currently working on a hybrid ‘instructional‐demonstration’ script and an ‘adventure‐game’ script. The main strengths and weaknesses of the Scald system are discussed, and suggesti

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00350.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

Abstract:This paper is concerned with structural models of what have come to be called Intelligent CAL systems. It proposes and examines such models in the light of the needs of different types of CAL systems, particularly those systems which offer learner control. Based on the five‐circle model proposed by Tim O’ Shea and others, a more general ‘figure of eight’ model is put forward which accords with certain of the ideas suggested by Gordon Pask concerning the architecture of learning

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00351.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00352.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00353.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

FIRST CLASS is an inductive expert system development tool written by William Hapgood and supplied by 1 st‐Class Expert Systems Inc. The product runs on IBM PC, XT and AT computers and close compatibles, running MS/DOS 2.0 or higher. It is sold in two versons, 1st‐Class (at $495 U.S.) and 1st‐Class Fusion (at $1295). This is a review of the plain version; but mention of ‘Fusion’ facilities is made where appropriate. 1st‐Class Expert Systems Inc. can be contacted at: 286 Boston Post Road, Wayland, Massachusetts 1778, USA (61

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00354.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY

摘要:

Abstract:Most existing expert systems store rules which guide programme behaviour. Inductive expert systems generate rules from properly formatted descriptions of historical data. The ID/3 algorithm, based on Earl Hunt's Concept Learning System, is among the more popular induction algorithms for this application. A general description of ID/3 is given along with suggestions for further possible refinements of the algorithm. Because ID/3 uses decision trees to store knowledge and does not inherently exclude the application of weights to paths through the tree, the algorithm bears a remarkable conceptual resemblance to neural networks. From this analogy some new applications for the algorithm are derived.

ISSN:0266-4720    

DOI:10.1111/j.1468-0394.1988.tb00355.x

出版商:Blackwell Publishing Ltd    

年代:1988

数据来源: WILEY