Search

Your search keyword '"Xu-Yao Zhang"' showing total 168 results
Start Over Author "Xu-Yao Zhang"
168 results on '"Xu-Yao Zhang"'

1. Potentialities and Challenges of mRNA Vaccine in Cancer Immunotherapy

Author

Li-Juan Duan, Qian Wang, Cuilian Zhang, Dong-Xiao Yang, and Xu-Yao Zhang

Subjects
mRNA, cancer vaccine, immunotherapy, efficient delivery, optimization, strategies, Immunologic diseases. Allergy, RC581-607
Abstract

Immunotherapy has become the breakthrough strategies for treatment of cancer in recent years. The application of messenger RNA in cancer immunotherapy is gaining tremendous popularity as mRNA can function as an effective vector for the delivery of therapeutic antibodies on immune targets. The high efficacy, decreased toxicity, rapid manufacturing and safe administration of mRNA vaccines have great advantages over conventional vaccines. The unprecedent success of mRNA vaccines against infection has proved its effectiveness. However, the instability and inefficient delivery of mRNA has cast a shadow on the wide application of this approach. In the past decades, modifications on mRNA structure and delivery methods have been made to solve these questions. This review summarizes recent advancements of mRNA vaccines in cancer immunotherapy and the existing challenges for its clinical application, providing insights on the future optimization of mRNA vaccines for the successful treatment of cancer.

Published
2022
Full Text
View/download PDF

2. From Class-Specific to Class-Mixture: Cascaded Feature Representations via Restricted Boltzmann Machine Learning

Author

Guo-Sen Xie, Xiao-Bo Jin, Xu-Yao Zhang, Shao-Fei Zang, Chunlei Yang, Zhiheng Wang, and Jiexin Pu

Subjects
Feature extraction, class-specific, RBM, feature learning, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

In this paper, we propose two kinds of feature extracting frameworks that can extract cascaded class-specific and class-mixture features, respectively, by taking the restricted Boltzmann machine (RBM) as the basic building blocks; we further call them as a CS-RBM and CM-RBM feature extractor. The discriminations of features from both CS-RBM and CM-RBM are verified better than the class-independent (traditional) RBM (CI-RBM) feature extractor. As one mini-batch samples are randomly selected from all classes during the training phase of the traditional RBM, which can make that the above mini-batch data contain easy-confusing samples from different categories. Therefore, the features from CI-RBM are difficult to distinguish these samples from the confused categories. CS-RBM and CM-RBM can overcome the above sample confusing problem efficiently and effectively. To cope with the real-valued input samples, we further extend the binary RBM to Gaussian-Bernoulli RBM (GBRBM), leading to the CS-GBRBM (CM-GBRBM) feature extracting framework. Experiments on binary datasets, i.e., MNIST and USPS, scene image dataset (Scene-15), and object image dataset (Coil-100), well verify the above facts and show the competitive results.

Published
2018
Full Text
View/download PDF

35. Learning by Seeing More Classes

Author

Fei Zhu, Xu-Yao Zhang, Rui-Qi Wang, and Cheng-Lin Liu

Subjects
Computational Theory and Mathematics, Artificial Intelligence, Applied Mathematics, Computer Vision and Pattern Recognition, Software
Abstract

Traditional pattern recognition models usually assume a fixed and identical number of classes during both training and inference stages. In this paper, we study an interesting but ignored question: can increasing the number of classes during training improve the generalization and reliability performance? For a k-class problem, instead of training with only these k classes, we propose to learn with k+m classes, where the additional m classes can be either real classes from other datasets or synthesized from known classes. Specifically, we propose two strategies for constructing new classes from known classes. By making the model see more classes during training, we can obtain several advantages. Firstly, the added m classes serve as a regularization which is helpful to improve the generalization accuracy on the original k classes. Secondly, this will alleviate the overconfident phenomenon and produce more reliable confidence estimation for different tasks like misclassification detection, confidence calibration, and out-of-distribution detection. Lastly, the additional classes can also improve the learned feature representation, which is beneficial for new classes generalization in few-shot learning and class-incremental learning. Compared with the widely proved concept of data augmentation (dataAug), our method is driven from another dimension of augmentation based on additional classes (classAug). Comprehensive experiments demonstrated the superiority of our classAug under various open-environment metrics on benchmark datasets.

Published
2023

43. A Survey on Learning to Reject

Author

Xu-Yao Zhang, Guo-Sen Xie, Xiuli Li, Tao Mei, and Cheng-Lin Liu

Subjects
Electrical and Electronic Engineering
Published
2023

Catalog

Books, media, physical & digital resources
See catalog results