報(bào) 告 人

S M Hasan Mahmud, Associate Professor, Department of Software Engineering,，Daffodil International University,，Bangladesh

報(bào)告時(shí)間

2025年4月12日（周六）下午15:30-16:00

報(bào)告地點(diǎn)

臺州學(xué)院科技綜合樓711

報(bào)

告

內(nèi)

容

簡

介

報(bào)告內(nèi)容簡介：

In recent years, the rise of deep learning has significantly advanced the performance of models across various domains. However, the effectiveness of these models heavily depends on the quality of labeled data. Noisy data labels—incorrect or imprecise annotations—pose a serious challenge, particularly when data is sourced from multiple or unreliable origins. This study explores the different data sources that contribute to label noise and highlights the diverse challenges associated with them, including class imbalance, mislabeled instances, and inconsistencies across datasets. We categorize label noise into symmetric and asymmetric types and analyze how these affect model training and generalization. Furthermore, this lecture focuses on key techniques developed to address these challenges, including robust loss functions, noise-tolerant algorithms, label correction methods, and semi-supervised learning approaches. Special emphasis is placed on the role of deep learning in mitigating the impact of noisy labels through architectures that inherently model uncertainty or adapt during training. By synthesizing current research and identifying practical solutions, this lecture aims to provide a comprehensive overview of the state-of-the-art in handling noisy labeled data.

報(bào)告人簡介：

Dr. S M Hasan Mahmud is an Associate Professor of Department of Software Engineering，Daffodil International University in Bangladesh. His research interests includes Bio-informatics,，Data Science,，Machine Learning，AI Drug Discovery and Health Informatics. He has over 40 publications as journal and conference papers. His google scholar citations are 1335 and total impact factor over 170.

承辦學(xué)院

電子與信息工程學(xué)院

發(fā)布日期

2025-4-8

歡迎廣大教師,、學(xué)生參加,！