Rapid advances in artificial intelligence (AI) in the last decade have been largely built upon
the wide applications of deep learning (DL). However, the high carbon footprint yielded by …

Background Network medicine is an emerging area of research that focuses on delving into
the molecular complexity of the disease, leading to the discovery of network biomarkers and …

The application of machine learning to image and video data often yields a high
dimensional feature space. Effective feature selection techniques identify a discriminant …

Chip defect detection plays an important role in the semiconductor production industry. The
breakage degree of the chip has a great impact on its performance. This paper proposes a …

Recent advances in unsupervised domain adaptation (UDA) show that transferable
prototypical learning presents a powerful means for class conditional alignment, which …

Abstract Vision-and-language (V & L) models take image and text as input and learn to
capture the associations between them. These models can potentially deal with the tasks …

On the basis of DefakeHop, an enhanced lightweight Deepfake detector called
DefakeHop++ is proposed in this work. The improvements lie in two areas. First, DefakeHop …

A feedforward-designed convolutional neural network (FF-CNN) is an interpretable neural
network with low training complexity. Unlike a neural network trained using backpropagation …

This work presents a generative modeling approach based on successive subspace
learning. Unlike most generative models in the literature, our method does not utilize neural …

A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this
work. Geo-DefakeHop is developed based on the parallel subspace learning (PSL) …