By Topic

An object-oriented hybrid environment for integrating neural networks and experts systems

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
S. Khebbal ; Dept. of Comput. Sci., London Univ., UK ; P. Treleaven

With the emerging realization that most complex real-world problems are difficult to solve by either symbolic or adaptive paradigms, there is great interest in combining the strengths of individual techniques (such as neural networks and expert systems), from these opposing forms of information processing. The object-oriented hybrid environment described allows the strengths of these contending processing paradigms to be combined for solving complex problems. The use of object-oriented methods brings with it many attributes and advantages for constructing hybrid systems. This approach allows each paradigm to be represented as an object, which can communicate with other paradigms via a message passing mechanism. The operation details of the neural-symbolic environment are illustrated and tested, with an application from the financial arena of profit trend analysis

Published in:

Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand International Two-Stream Conference on

Date of Conference:

24-26 Nov 1993