Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments

TL;DR

This paper presents a systematic framework using design of experiments to evaluate the robustness of AI classification algorithms across various factors like data imbalance and distribution shifts.

Contribution

It introduces a novel experimental framework for assessing AI robustness and provides insights into how different factors influence AI performance stability.

Findings

Robustness is significantly affected by class imbalance and distribution shifts.

Certain algorithms demonstrate higher stability under varied conditions.

Statistical analysis reveals key factors impacting AI robustness.

Abstract

Artificial intelligent (AI) algorithms, such as deep learning and XGboost, are used in numerous applications including computer vision, autonomous driving, and medical diagnostics. The robustness of these AI algorithms is of great interest as inaccurate prediction could result in safety concerns and limit the adoption of AI systems. In this paper, we propose a framework based on design of experiments to systematically investigate the robustness of AI classification algorithms. A robust classification algorithm is expected to have high accuracy and low variability under different application scenarios. The robustness can be affected by a wide range of factors such as the imbalance of class labels in the training dataset, the chosen prediction algorithm, the chosen dataset of the application, and a change of distribution in the training and test datasets. To investigate the robustness of AI classification algorithms, we conduct a comprehensive set of mixture experiments to collect prediction performance results. Then statistical analyses are conducted to understand how various factors affect the robustness of AI classification algorithms. We summarize our findings and provide suggestions to practitioners in AI applications.