Abstract not found

: We propose a theoretical framework allowing a real integration of Machine Learning and Knowledge acquisition. This article shows that the input of a Machine Learning system can be mapped to the model of expertise as it is used in KADS methodology. The notion of learning bias will play a central role. We shall see that parts of it can be identified to what people are used to call the inference and the task models. We shall also see that the description language and its structure, i.e., the background knowledge, can be mainly related to the domain model. Doing this conceptual mapping, we give a status to most of the inputs of Machine Learning programs in terms of knowledge acquisition models. The ENIGME system which implements this work will be presented in this paper. It will show a way to integrate a machine learning algorithm into a knowledge acquisition environment. Keywords: knowledge acquisition, models of knowledge, learning bias, empirical learning. 1. INTRODUCTION How Machine...

A case study on integrating contextual information with analytical usability evaluation

considerations for effective knowledge acquisition:

Conventional approaches to knowledge acquisition take it for granted that as a result of the investigation an expert system will be developed. The methods used therefore focus on the knowledge that will be used in these systems. This paper argues, however, that the issues of the knowledge used in organisational problem solving need to be seen in a wider context than this, and that the agenda for knowledge acquisition should be widened to incorporate this full context. The extent to which the methods used for knowledge acquisition can be more broadly useful for organisational problem solving without creating an expert system is explained. The implications of this view are discussed and a number of practical suggestions are made. The research described in this paper was partially funded by a Commission of European Communities ESPRIT programme Exploratory Action, Number 5639. 1 Knowledge acquisition for organisational problem solving: Developing expert systems and beyond Conventional approaches to knowledge acquisition take it for granted that as a result of the investigation an expert system will be developed. The methods used therefore focus on the knowledge that will be used in these systems. This paper argues, however, that the issues of the knowledge used in organisational problem solving need to be seen in a wider context than this, and that the agenda for knowledge acquisition should be widened to incorporate this full context. The extent to which the methods used for knowledge acquisition can be more broadly useful for organisational problem solving without creating an expert system is explained. The implications of this view are discussed and a number of practical suggestions are made. 2