Visualizing the Function Computed by a Feedforward Neural Network

Authors:
Tony A. Plate;Joel A. Bert;John A. Grace;Pierre A. Band
Affiliations:
Bios Group LP, Santa Fe, NM 87501, U.S.A.;Department of Chemical Engineering, University of British Columbia, Vancouver, BC, V6T 1Z4, Canada;Department of Chemical Engineering, University of British Columbia, Vancouver, BC, V6T 1Z4, Canada;Environmental Health Centre, Health Canada, Ottawa, Ontario, K1A OL2, Canada
Venue:
Neural Computation
Year:
2000

Citing 3
Cited 3

Extracting Refined Rules from Knowledge-Based Neural Networks

Machine Learning
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Bootstrapping confidence intervals for clinical input variable effects in a network trained to identify the presence of acute myocardial infarction

Neural Computation

Evaluation of prediction capability, robustness, and sensitivity in non-linear landslide susceptibility models, Guantánamo, Cuba

Computers & Geosciences
Integrating spectral indices with environmental parameters for estimating heavy metal concentrations in rice using a dynamic fuzzy neural-network model

Computers & Geosciences
Neural networks for probabilistic environmental prediction: Conditional Density Estimation Network Creation and Evaluation (CaDENCE) in R

Computers & Geosciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.