Significance Tests for Neural Networks
Preprint
Abstract
We develop a pivotal test to assess the statistical significance of the feature variables in a single-layer feedforward neural network regression model. We propose a gradient-based test statistic and study its asymptotics using nonparametric techniques. Under technical conditions, the limiting distribution is given by a mixture of chi-square distributions. The tests enable one to discern the impact of individual variables on the prediction of a neural network. The test statistic can be used to rank variables according to their influence. Simulation results illustrate the computational efficiency and the performance of the test. An empirical application to house price valuation highlights the behavior of the test using actual data.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- A Survey of Methods for Explaining Black Box ModelsACM Computing Surveys, 2018
- Bootstrap non-parametric significance testJournal of Nonparametric Statistics, 2007
- Statistical inference, the bootstrap, and neural-network modeling with application to foreign exchange ratesIEEE Transactions on Neural Networks, 2001
- Improved rates and asymptotic normality for nonparametric neural network estimatorsIEEE Transactions on Information Theory, 1999
- On the Geometry of Feedforward Neural Network Error SurfacesNeural Computation, 1993
- A Consistent Model Specification Test for Nonparametric Estimation of Regression Function ModelsEconometric Theory, 1993
- Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappingsNeural Networks, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Learning in Artificial Neural Networks: A Statistical PerspectiveNeural Computation, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989