In this paper, we study the problem of embedding uncertain knowledge graphs, where each relation between entities is associated with a confidence score. Observing existing methods may discard uncertainty information, only incorporate specific type score function, or cause many false-negative samples in training, propose PASSLEAF framework to solve above issues. consists two parts, one model tha...

Recent advances in supervised deep learning methods are enabling remote measurements of photoplethysmography-based physiological signals using facial videos. The performance these methods, however, dependent on the availability large labelled data. Contrastive as a self-supervised method has recently achieved state-of-the-art performances representative data features by maximising mutual inform...

of thesis entitled: Statistical Machine Learning for Data Mining and Collaborative Multimedia Retrieval Submitted by HOI, Chu Hong (Steven) for the degree of Doctor of Philosophy at The Chinese University of Hong Kong in September 2006 Statistical machine learning techniques have been widely applied in data mining and multimedia information retrieval. While traditional methods, such as supervis...

Unsupervised image segmentations are usually implemented without human interactions, but the segmentation is sometime incorrect for complicated images, especially when the features of different classes are very close. On the other hand, supervised image segmentation, utilizing the features obtained by machine-learning and then applying some classification algorithms to the features, can usually...

Automated machining feature recognition is an essential component linking computer-aided design (CAD) and process planning (CAPP). Deep learning (DL) has recently emerged as a promising method to improve recognition. However, training DL-based models typically require annotating large amounts of data, which time-consuming labor-intensive for researchers. Additionally, DL struggle achieve satisf...

This work proposes a supervised multi-channel time-series learning framework for financial stock trading. Although many deep models have recently been proposed in this domain, most of them treat the trading data as 2-D image data, whereas its true nature is 1-D data. Since systems are existing techniques treating not suggestive any technique to effectively fusion information carried by multiple...

The elastic net is among the most widely used types of regularization algorithms, commonly associated with problem supervised generalized linear model estimation via penalized maximum likelihood. Its attractive properties, originated from a combination ?1 and ?2 norms, endow this method ability to select variables, taking into account correlations between them. In last few years, semi-supervise...

We consider a framework for semi-supervised learning using spectral decomposition based un-supervised kernel design. This approach subsumes a class of previously proposed semi-supervised learning methods on data graphs. We examine various theoretical properties of such methods. In particular, we derive a generalization performance bound, and obtain the optimal kernel design by minimizing the bo...