An Approach to Finding a Robust Deep Learning Model

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexey Boldyrev, Fedor Ratnikov, Andrey Shevelev
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11030460/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2169-3536