学术报告:Handling Class Imbalance and Small Sample Issues: Foundation, Algorithms, and Applications-武汉大学计算机学院

学术报告:Handling Class Imbalance and Small Sample Issues: Foundation, Algorithms, and Applications

发布时间:2024-10-30     浏览量:

报告题目:Handling Class Imbalance and Small Sample Issues: Foundation, Algorithms, 

                    and Applications

报告时间:202411115:00-16:30

报告地点:计算机学院B405

报告人:王子栋

报告人单位:英国伦敦Brunel大学

报告人简介:王子栋,现任英国伦敦Brunel University讲席教授,欧洲科学院院士,欧洲科学与艺术院院士,IEEE FellowInternational Journal of Systems Science主编,Neurocomputing主编。多年来从事控制理论、机器学习、生物信息学等方面研究,在SCI刊物上发表国际论文七百余篇。现任或曾任十二种国际刊物的主编、副编辑或编委。曾任旅英华人自动化及计算机协会主席、东华大学国家级领军人才、清华大学国家级专家。

报告摘要In big data analysis, it is usually difficult to collect high-quality labels, and this leads to two issues in deep learning, namely, the class imbalance issue and the small sample issue. In this talk, we first introduce some background knowledge about the deep learning from the perspectives of concepts, techniques, applications and challenges. Then, we introduce three state-of-the-art algorithms for solving the class imbalance and small sample issues: 1) a novel contrastive adversarial network for minor-class data augmentation; 2) a novel subdomain-alignment data augmentation approach; and 3) a novel prototype-assisted contrastive adversarial network for weak-shot learning. All the three algorithms are applied to pipeline fault diagnosis, which outperform existing ones. Finally, we conclude our main contributions and some future directions.

邀请人:杜博