Thread View: bne.seminar
1 messages
1 total messages
Started by Tony Rhodes
Fri, 09 Apr 1999 00:00
Automated refinement of a knowledge base
Author: Tony Rhodes
Date: Fri, 09 Apr 1999 00:00
Date: Fri, 09 Apr 1999 00:00
33 lines
1942 bytes
1942 bytes
You are invited to attend the following seminar:
Speaker: Robert Andrews
Lecturer
School of Information Systems
Queensland University of Technology
Title: RULEIN/RULEX, an automoated technique for the refinement of a
knowledge base.
Date: Monday, 12th April 1999
Time: 12.00pm
Place: Lecture Theatre S303, Faculty of Information Technology,
Queensland University of Technology
Abstract:
---------
This talk describes RULEIN/RULEX, an automoated technique for the
refinement of a knowledge base. RULEIN constructs a Rapid Backprop (RBP)
artificial neural network from an initial, partially complete/accurate
knowledge base which is given as a set of propositionla rules. The RBP
network is trained on a set of examples drawn from the problem domain.
RULEX is then used to extract a set of 'refined' propositional rules from
the weights of the trained network. The refined rules represent the
original knowledge base modified in the light of network training. Results
demonstrate that the use of prior knowledge in this manner can decrease
network training time and bias the learning away from local minima. The
method has many applications but is particularly well suited to overcoming
the so called 'knowledge acquisition bottleneck' in the knowledge
engineering phase of rule based expert system construction.
---
For further information please contact me.
Thread Navigation
This is a paginated view of messages in the thread with full content displayed inline.
Messages are displayed in chronological order, with the original post highlighted in green.
Use pagination controls to navigate through all messages in large threads.
Back to All Threads