Abstract
dc:description.abstract<p>Many rule-based learning systems have been implemented which generate and update rules/facts from illustrative examples provided by the user. But very few of them have succeeded in achieving the efficiency and accuracy of an ideal system.</p><p>The approach made here is to continuously update the hierarchical structure of rules/facts of a knowledge-base so that efficient and accurate solutions to any query can be achieved easily and immediately from the many possible solutions to the query. As the rule-based systems deal with a very large knowledge-base, it is sometimes necessary to apply a learning technique that finds optimum solutions efficiently.</p><p>The above approach has been implemented based on associated probabilities with each rule/fact at all nodes of the search tree. The learning system implemented here permits two types of user interventions. The user provides the rules/facts with the associated probabilities and can also alter the search priority during query solving. However, in the former case, inaccuracy by the user in making the system learn optimum solutions to a query, may lead to an inefficient and inaccurate system. The learning system has been implemented in LISP under the UNIX environment.</p>
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Electrical Engineering - (M.S.)
- Discipline thesis:degree_discipline
- Electrical Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Adani, Bhavesh T.
- Contributors dc:contributor
-
- Stanley S. Reisman
- John D. Carpinelli
Subjects
dc:subject × 3Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.njit.edu/theses/3001