Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …

Image classification systems recently made a giant leap with the advancement of deep
neural networks. However, these systems require an excessive amount of labeled data to be …

This chapter provides theoretical insights into why and how deep learning can generalize
well, despite its large capacity, complexity, possible algorithmic instability, non-robustness …

Datasets with significant proportions of noisy (incorrect) class labels present challenges for
training accurate Deep Neural Networks (DNNs). We propose a new perspective for …

We consider two questions at the heart of machine learning; how can we predict if a
minimum will generalize to the test set, and why does stochastic gradient descent find …

Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming
industry applications and generating new and improved capabilities for scientific discovery …

Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural
Networks (DNNs), including both production quality, pre-trained models such as AlexNet …

We present an information-theoretic framework for understanding overfitting and underfitting
in machine learning and prove the formal undecidability of determining whether an arbitrary …

The recent success of deep learning is mostly due to the availability of big datasets with
clean annotations. However, gathering a cleanly annotated dataset is not always feasible …