As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing
DNNs become more complex and diverse, ranging from improving a conventional model …

Research of visual neural networks (VNNs) is one of the most important topics in deep
learning and has received wide attention from industry and academia for their promising …

Interpreting the decisions of deep learning models has been actively studied since the
explosion of deep neural networks. One of the most convincing interpretation approaches is …

Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable
classification by associating predictions with a set of training prototypes, which we refer to as …

Integrated with the state-of-the-art technologies, Artificial Intelligence (AI) has been
successfully applied to diverse industries thanks to the increased availability of data and …

Recently a wide variety of NAS methods have been proposed and achieved considerable
success in automatically identifying highly-performing architectures of neural networks for …

Despite being highly performant, deep neural networks might base their decisions on
features that spuriously correlate with the provided labels, thus hurting generalization. To …

There is a growing concern about typically opaque decision-making with high-performance
machine learning algorithms. Providing an explanation of the reasoning process in domain …

Post-hoc explanation methods, eg, Grad-CAM, enable humans to inspect the spatial regions
responsible for a particular network decision. However, it is shown that such explanations …

Deep learning classifiers achieve state-of-the-art performance in various risk detection
applications. They explore rich semantic representations and are supposed to automatically …