Machine learning (ML) has emerged as the principal tool for performing complex tasks
which are impractical (if not impossible) to code by humans. ML techniques provide …

In federated learning for medical image analysis, the safety of the learning protocol is
paramount. Such settings can often be compromised by adversaries that target either the …

This book discusses the technological aspects for the implementation of Society 5.0. The
foundation and recent advances of emerging technologies such as artificial intelligence …

This dissertation tackles the issues of improving and evaluating the robustness of machine
learning models for medical diagnosis. We describe a data augmentation technique that …

Abstract Deep Neural Networks (DNNs) have transformed the field of multimedia generation
and recognition by replacing traditional hand-engineered systems in domains like vision …

Deep Learning (DL) applications are widely deployed in diverse areas, such as image
classification, natural language processing, and auto-driving systems. Although these …

Machine Learning (ML) has emerged in recent years as a transformative technology,
advancing the state-of-the-art in diverse domains such as image and voice recognition …

This thesis studies the merits of applying log-gradient input images to convolutional neural
networks (CNNs) for tinyML computer vision (CV). We show that log gradients enable:(i) …

With the growing demand for real-time intelligence driven by device-to-device (D2D)
communication, deploying Deep Learning (DL) applications at the network edge becomes …

Despite the fact that deep learning techniques have achieved tremendous success, their
underlying models are vulnerable to Adversarial Examples (AEs) and Trojan attacks. AEs …