Explaining Predictions from a Neural Network Ensemble One at a Time

Authors:
Robert Wall;Padraig Cunningham;Paul Walsh
Affiliations:
-;-;-
Venue:
PKDD '02 Proceedings of the 6th European Conference on Principles of Data Mining and Knowledge Discovery
Year:
2002

Citing 7
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Neural expert systems

Neural Networks
Bagging predictors

Machine Learning
Knowledge-based neurocomputing

Knowledge-based neurocomputing
Neural Network Ensembles

IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Diversity in Preparing Ensembles of Classifiers Based on Different Feature Subsets to Minimize Generalization Error

EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Stability problems with artificial neural networks and the ensemble solution

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new method for explaining the predictions of ensembles of neural networks on a case by case basis. The approach of explaining individual examples differs from much of the current research which focuses on producing a global model of the phenomenon under investigation. Explaining individual results is accomplished by modelling each of the networks as a rule-set and computing the resulting coverage statistics for each rule given the data used to train the network. This coverage information is then used to choose the rule or rules that best describe the example under investigation. This approach is based on the premise that ensembles perform an implicit problem space decomposition with ensemble members specialising in different regions of the problem space. Thus explaining an ensemble involves explaining the ensemble members that best fit the example.