Approach to Finding a Robust Deep Learning Model
This addresses the need for unsupervised training of reliable models in ML/AI applications, but it appears incremental as it builds on existing robustness evaluation methods.
The paper tackles the problem of ensuring reliable predictions in deep learning models by proposing a novel approach for determining model robustness, supplemented with a versatile meta-algorithm for model selection, and demonstrates its application on small convolutional and fully connected models to study factors like training sample size and weight initialization.
The rapid development of machine learning (ML) and artificial intelligence (AI) applications requires the training of 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 proposed 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 due to their ease of interpretation and computational efficiency. Within this framework, we address the influence of training sample size, model weight initialization, and inductive bias on the robustness of deep learning models.