A Neural Network Truth Maintenance System
نویسندگان
چکیده
منابع مشابه
Network-based Truth Maintenance System
1 Charles River Analytics, Inc., 625 Mount Auburn St., Cambridge, MA 02138, USA. Email: {sdas, dlawless}@cra.com Abstract We present a Network-based Truth Maintenance System (NTMS) for problem solvers based on Bayesian belief network (BN) technology. BN technology has been proven to be effective in various domains, e.g. assessing battlefield situations, such as the enemy’s likely point of inter...
متن کاملA Truth Maintenance System
To choose their actions, reasoning programs must be able to make assumptions and subsequently revise their beliefs when discoveries contradict these assumptions. The Truth Maintenance System (TMs) is a problem solver subsystem for performing these functions by recording and maintaining the reasons for program beliefs. Such recorded reasons are useful in constructing explanations of program acti...
متن کاملAn application of artificial neural network to maintenance management
This study shows the usefulness of Artificial Neural Network (ANN) in maintenance planning and man-agement. An ANN model based on the multi-layer perceptron having three hidden layers and four processing elements per layer was built to predict the expected downtime resulting from a breakdown or a maintenance activity. The model achieved an accuracy of over 70% in predicting the expected downtime.
متن کاملMultiagent Truth Maintenance Applied to a Tourism Recommender System
The Internet is a rich source of information where users search for contents about products and services related to their interests and preferences. However, this has generated some problems. In fact, the overload of information may divert the users and ultimately make it very hard to locate the desired information (Maes, 1994). Moreover, the relevant data required is usually distributed over s...
متن کاملTruth Maintenance Under Uncertainty
This paper addresses the problem of resolving errors under uncertainty in a rule-based sys tem. A new approach has been developed that reformulates this problem as a neural-network learning problem. The strength and the fun damental limitations of this approach are ex plored and discussed. The main result is that neural heuristics can be applied to solve some but not all problems in rule-bas...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Dynamic Systems, Measurement, and Control
سال: 1991
ISSN: 0022-0434,1528-9028
DOI: 10.1115/1.2896349