Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

8

IDEAL
2005
Springer

favoriteEmaildiscussreport

97views Intelligent Agents» more IDEAL 2005»

Generating Predicate Rules from Neural Networks

13 years 9 months ago

Generating Predicate Rules from Neural Networks

Download eprints.qut.edu.au

Artiﬁcial neural networks play an important role for pattern recognition tasks. However, due to poor comprehensibility of the learned network, and the inability to represent explanation structures, they are not considered suﬃcient for the general representation of knowledge. This paper details a methodology that represents the knowledge of a trained network in the form of restricted ﬁrst-order logic rules, and subsequently allows user interaction by interfacing with a knowledge based reasoner.

Richi Nayak

Real-time Traffic

Artiﬁcial Neural Networks | IDEAL 2005 | Knowledge Based Reasoner | Pattern Recognition Tasks |

claim paper

Related Content

» Extraction of Logical Rules from Neural Networks

» Extraction of Symbolic Rules from Artificial Neural Networks

» An Algorithm to Extract Rules from Artificial Neural Networks for Medical Diagnosis Proble...

» CrySSMEx a Novel Rule Extractor for Recurrent Neural Networks Overview and Case Study

» Generating Entailment Rules from FrameNet

» NeuroRule A Connectionist Approach to Data Mining

» Extraction of similarity based fuzzy rules from artificial neural networks

» An Associative Memory for Association Rule Mining

» Indirectly Encoding Neural Plasticity as a Pattern of Local Rules

Post Info
More Details (n/a)

Added	27 Jun 2010
Updated	27 Jun 2010
Type	Conference
Year	2005
Where	IDEAL
Authors	Richi Nayak

Comments (0)