An Approach to Finding a Robust Deep Learning Model

IEEE Access. 2025. Vol. 13. P. 102390–102406.

Boldyrev A., Ratnikov F., Shevelev A.

The rapid development of machine learning (ML) and artificial intelligence (AI) applications
requires the training of a large numbers of models. This growing demand highlights the importance of
training models without human supervision, while ensuring that their predictions are reliable. In response
to this need, we propose a novel approach for determining model robustness. This approach, supplemented
with a model selection algorithm designed as a meta-algorithm, is versatile and applicable to any machine
learning model, provided that it is appropriate for the task at hand. This study demonstrates the application
of our approach to evaluate the robustness of deep learning models. To this end, we study small models
composed of a few convolutional and fully connected layers, using common optimizers because of their
ease of interpretation and computational efficiency. We address the influence of training sample size, model
weight initialization, and inductive bias on the robustness of deep learning models.

Keywords: машинное обучение, робастность, deep learning, глубинное обучение, Robustness, machine learning