HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Plate, T. A. Articles by Band, P. Search for Related Content PubMed PubMed Citation Articles by Plate, T. A. Articles by Band, P.

Visualizing the Function Computed by a Feedforward Neural Network

Bios Group LP, Santa Fe, NM 87501, U.S.A.

Joel Bert

Department of Chemical Engineering, University of British Columbia, Vancouver, BC, V6T 1Z4, Canada

John Grace

Department of Chemical Engineering, University of British Columbia, Vancouver, BC, V6T 1Z4, Canada

Pierre Band

Environmental Health Centre, Health Canada, Ottawa, Ontario, K1A OL2, Canada

A method for visualizing the function computed by a feedforward neural network is presented. It is most suitable for models with continuous inputs and a small number of outputs, where the output function is reasonably smooth, as in regression and probabilistic classification tasks. The visualization makes readily apparent the effects of each input and the way in which the functions deviate from a linear function. The visualization can also assist in identifying interactions in the fitted model. The method uses only the input-output relationship and thus can be applied to any predictive statistical model, including bagged and committee models, which are otherwise difficult to interpret. The visualization method is demonstrated on a neural network model of how the risk of lung cancer is affected by smoking and drinking.