|
Integrating Rule Based and Neural Net Processing.
The purpose of havCNet is to provide a mechanism by which users can integrate Expert Systems and Neural Nets. It is intended that either will be capable of using the other - which is to say -
|
![]() |
One or more networks can be consulted (or trained - though this seems unlikely) from either the proposition (LHS) or consequent (RHS) of a rule. |
![]() |
A Network can either issue a query or force an inference cycle of any rule-sets in memory. |
![]() |
A Network must also be able to modify the current fact-list. |
|
Expert System processing will be provided by Clips.
Neural Net processing will be implemented using the havBpNet++ and havFmNet++ libraries.
|
|
|
|
Home ||
Services & Clients ||
Products ||
WIPs ||
Orders ||
News
Bonsai Pic's ||
Bonsai Style ||
Bonsai Databases ||
Bonsai Icons
Copyright © -1995-2008 by hav.Software. All Rights Reserved.
Java and all Java-based marks are trademarks or registered trademarks of Sun Microsystems, Inc. in the U.S. and other countries. There may be other trademarks or tradenames listed in this document to refer to the entities claiming the marks and names or products. hav.Software disclaims any proprietary interest in any trademark, tradename or products other than its own. Modified - 08/07/99 - 14739023 - 4127468 |