Statistical tuning of artificial neural network

TL;DR

This paper introduces statistical methods and tests to interpret and simplify single-hidden-layer neural networks, enhancing their explainability and performance evaluation.

Contribution

It develops a theoretical framework linking neural networks to nonparametric regression and proposes statistical tools for neuron significance testing and dimensionality reduction.

Findings

Bootstrap performance evaluation method for ANNs

Statistical tests for neuron significance and efficiency

Application to IDC and Iris datasets validates methods

Abstract

Neural networks are often regarded as "black boxes" due to their complex functions and numerous parameters, which poses significant challenges for interpretability. This study addresses these challenges by introducing methods to enhance the understanding of neural networks, focusing specifically on models with a single hidden layer. We establish a theoretical framework by demonstrating that the neural network estimator can be interpreted as a nonparametric regression model. Building on this foundation, we propose statistical tests to assess the significance of input neurons and introduce algorithms for dimensionality reduction, including clustering and (PCA), to simplify the network and improve its interpretability and accuracy. The key contributions of this study include the development of a bootstrapping technique for evaluating artificial neural network (ANN) performance, applying statistical tests and logistic regression to analyze hidden neurons, and assessing neuron efficiency. We also investigate the behavior of individual hidden neurons in relation to out-put neurons and apply these methodologies to the IDC and Iris datasets to validate their practical utility. This research advances the field of Explainable Artificial Intelligence by presenting robust statistical frameworks for interpreting neural networks, thereby facilitating a clearer understanding of the relationships between inputs, outputs, and individual network components.