Interpretable Architecture Neural Networks for Function Visualization

DOI10.1080/10618600.2023.2195461MaRDI QIDQ6181398zbMATH OpenFDO

Authors Shengtong Zhang, Daniel W. Apley

Publication date 22 January 2024

Published in Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2303.03393

zbMATH Keywords

function visualizationinterpretable machine learningneural network

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: In many scientific research fields, understanding and visualizing a black-box function in terms of the effects of all the input variables is of great importance. Existing visualization tools do not allow one to visualize the effects of all the input variables simultaneously. Although one can select one or two of the input variables to visualize via a 2D or 3D plot while holding other variables fixed, this presents an oversimplified and incomplete picture of the model. To overcome this shortcoming, we present a new visualization approach using an interpretable architecture neural network (IANN) to visualize the effects of all the input variables directly and simultaneously. We propose two interpretable structures, each of which can be conveniently represented by a specific IANN, and we discuss a number of possible extensions. We also provide a Python package to implement our proposed method. The supplemental materials are available online.

Cites work

• All models are wrong, but many are useful: learning a variable's importance by studying an entire class of prediction models simultaneously
• Approximation by superpositions of a sigmoidal function
• Bayesian calibration of computer models. (With discussion)
• Bayesian Design and Analysis of Computer Experiments: Use of Derivatives in Surface Prediction
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Enhanced topology-sensitive clustering by Reeb graph shattering
• Greedy function approximation: A gradient boosting machine.
• Multilayer feedforward networks are universal approximators
• Predicting the output from a complex computer code when fast approximations are available
• Quasi-regression
• Random forests
• Scikit-learn: machine learning in Python
• Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models

Cited in

(1)

• Bivariate DeepKriging for Large-Scale Spatial Interpolation of Wind Fields

This page was built for publication: Interpretable Architecture Neural Networks for Function Visualization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6181398)