Abstract
We investigate methods for tuning numeric parameters in Nynex MAX, a telephone trouble screening expert system. Steepest descent, hillclimbing, and simulated annealing parameter adjustment strategies are applied to the problems of maximizing classification accuracy and minimizing misclassification cost. For both of those optimization problems we evaluate each algorithm''s ability to tune initial parameters for several situations
Recommended Citation
C. J. Merz and M. J. Pazzani, "Parameter Tuning for the MAX Expert System," Proceedings of the 6th International Conference on Tools with Artificial Intelligence, 1994, Institute of Electrical and Electronics Engineers (IEEE), Jan 1994.
The definitive version is available at https://doi.org/10.1109/TAI.1994.346450
Meeting Name
6th International Conference on Tools with Artificial Intelligence, 1994
Department(s)
Computer Science
Keywords and Phrases
MAX Expert System; Nynex MAX; Steepest Descent; Classification Accuracy; Diagnostic Expert Systems; Hillclimbing; Initial Parameters; Misclassification Cost; Numeric Parameters; Optimization Problems; Parameter Tuning; Simulated Annealing; Simulated Annealing Parameter Adjustment Strategies; Telecommunication Computing; Telephone Trouble Screening Expert System; Telephony
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1994 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
01 Jan 1994