To facilitate crossing from the "black box" to "glass box" in the application of neural networks (NNs), we develop a variable significant test for the multi-layer perceptrons. To derive the test statistic and its asymptotic distribution, we provide the consistency of the multi-layer perceptrons...

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...

To facilitate crossing from the "black box" to "glass box" in the application of neural net- works, we extend Horel and Giesecke (2020) and develop a variable/feature significant test for multi-layer perceptrons (MLP). The proposed test permits one to assess the statistical significance of the...