Thumbnail
Access Restriction
Open

Author Wall, Robert ♦ Cunningham, Padraig ♦ Walsh, Paul
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Case Basis ♦ Global Model ♦ Dierent Region ♦ Coverage Statistic ♦ Coverage Information ♦ Individual Example Diers ♦ Neural Network ♦ Current Research ♦ Individual Explanation ♦ Ensemble Member ♦ Implicit Problem Space Decomposition ♦ Problem Space ♦ Neural Network Ensemble One ♦ New Method
Description 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 diers from much of the current research which focuses on producing a global model of the phenomenon under investigation. This individual explanation is accomplished by modelling each of the networks as a rule-set and computing 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 perspective that ensembles perform an implicit problem space decomposition with ensemble members specialising in dierent regions of the problem space.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2002-01-01
Publisher Institution In PKDD 2002