Using neural networks to automatically refine expert system knowledge bases: experiments in the NYNEX MAX domain

We describe our study of applying knowledge-based neural networks to the problem of diagnosing faults in local telephone loops. Currently, NYNEX uses an expert system called MAX to aid human experts in diagnosing these faults; however, having an effective learning algorithm in place of MAX would all...

Full description

Saved in:
Bibliographic Details
Main Authors: Opitz, D.W., Craven, M.W., Shavlik, J.W.
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Computer networks
Computer science
Decision trees
Diagnostic expert systems
Expert systems
Humans
Intelligent networks
Neural networks
Telephony
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe our study of applying knowledge-based neural networks to the problem of diagnosing faults in local telephone loops. Currently, NYNEX uses an expert system called MAX to aid human experts in diagnosing these faults; however, having an effective learning algorithm in place of MAX would allow easy portability between different maintenance centers, and easy updating when the phone equipment changes. We find that (i) machine learning algorithms have better accuracy than MAX, (ii) neural networks perform better than decision trees, (iii) neural network ensembles perform better than standard neural networks, (iv) knowledge-based neural networks perform better than standard neural networks, and (v) an ensemble of knowledge-based neural networks performs the best.
DOI:10.1109/ICNN.1997.611627