Speaker:  Prof. Qi Ye(叶颀教授)

Time: 12:10-13:10, 8 December 2023 (Friday) (Beijing time)

Venue: C305, Lijiao Building, BNU

Tencent Meeting ID: 647-571-023


Abstract

In this talk, we show a new mathematical framework of machine learning to combine the data driven methods and model-driven methods. Usually the data-driven methods and model driven methods are used to introduce the black-box algorithms and white-box algorithms, respectively. The original idea is to use the local information of multimodal data and multiscale models to construct the global approximate solutions by the learning algorithms. The work of the composite algorithms provides another road to study the mathematical theory of machine learning including the interpretability in approximation theory, the nonconvexity and nonsmoothness in optimization theory, and the generalization and overfitting in regularization theory. For our project of computational medicine for pancreatic cancer, we study the composite algorithm of image processing and modeling simulation.


About Prof. Ye

叶颀现任华南师范大学数学科学学院教授、博士生导师,主要研究方向为逼近论及其在机器学习与数据分析中的应用。他在美国伊利诺理工大学攻读博士学位期间师从核函数逼近方法专家 Gregory E. Fasshauer教授,博士毕业后前往美国雪城大学与计算数学专家许跃生教授开展博士后研究工作,随后又赴香港与径向基函数专家韩耀宗教授和凌立云教授开展合作研究。他入选国家高层次人才特殊支持计划科技创新领军人才项目、国家海外高层次人才引进计划青年项目,担任国家自然科学基金数学天元基金“数学与医疗健康交叉重点专项”项目负责人,主持广东高校重大科研项目和重点领域专项等。他学成归国后采用“抽象理论、具体算法、实际应用”三位一体的研究新模式,联合国内外专家学者在广州成立了“机器学习与最优化计算实验室”,聚焦机器学习方法和大数据分析的原创性数学理论,研究核函数逼近方法、非光滑分析、医学图像处理、癌症演化建模等前沿课题,积极推动人工智能算法的基础理论研究及其在医疗和教育大数据中的实际应用,研发具有自主知识产权的医疗和教育辅助软件,促进粤港澳大湾区精准医疗和智能教育的发展。