應yl7703永利官網李朋副教授邀請,華南師范大學數(shù)學科學 學院葉頎教授, 將于2022年11月3號(星期四)上午9:00在線舉辦學術報告.詳情見http:/info/1065/4039.htm

報告題目：Machine Learning in Banach Spaces: A Black-box or White-box Method?

騰訊會議ID:609-555-634

報告摘要:In this talk, we study the whole theory of regularized learning for generalized data in Banach spaces including representer theorems, approximationtheorems, and convergence theorems. Specially, we combine the data-driven and model-driven methods to study the new algorithms and theorems of the regularized learning. Usually the data-driven and model-driven methods are used to analyze the black-box and white-box models, respectively. With the same thought of the Tai Chi diagram, we use the discrete local information of the black-box and white-box models to construct the global approximate solutions by the regularized learning. Our original ideas are inspired by the eastern philosophy such as the golden mean. The work of the regularized learning for generalized data provides another road to study the algorithms of machine learning including

(a)the interpretability in approximation theory,

(b)the nonconvexity and nonsmoothness in optimization theory,

(c)the generalization and overfitting in regularization theory.Moreover, based on the theory of the regularized learning, we will construct the composite algorithms combining support vector machines, artificial neural networks, and decision trees for our current research projects of the big data analytics in education and medicine.

報告人簡介

葉頎,現(xiàn)任華南師范大學數(shù)學科學學院的教授和博士生導師, 一直從事核函數(shù) 逼近方法的理論及其應用研究. 葉教授在美國伊利諾理工大學（Illinois Institute of Technology）博士學習期間師從核函數(shù)逼近方法專家Gregory E. Fasshauer教授, 博士畢業(yè)后到美國雪城大學(Syracuse University)與計算數(shù)學專家許躍生教授展開博士后研究工作, 之后又到香港與徑向基函數(shù)專家韓耀宗教授和凌立云教授展開合作研究. 葉教授入選國家海外高層次人才引進計劃青年項目, 擔任國家自然科學基金數(shù)學天元基金“數(shù)學與醫(yī)療健康交叉重點專項”項目負責人, 主持廣東省教育廳廣東高校重大科研項目等. 葉教授主要的研究方向是逼近論及其在機器學習與數(shù)據(jù)分析中的應用, 并和許教授共同提出了國際原創(chuàng)性研究課題——稀疏機器學習方法, 相關的122頁論文《Generalized Mercer Kernels and Reproducing Kernel Banach Spaces》發(fā)表在了美國數(shù)學學會主辦的期刊《Memoirs of the American Mathematical Society》(該期刊每期只刊登一篇文章), 并是該期刊發(fā)表 的首篇關于機器學習的論文, 也是國內計算數(shù)學工作者首次在該期刊發(fā)表的長文.

葉教授在華南師范大學采用“抽象理論、具體算法、落地應用”三位一體的科研新模式, 聯(lián)合國內外專家學者成立了“機器學習與最優(yōu)化計算實驗室”, 以機器學習方法的數(shù)學理論為主要研究目標, 研究范疇包括逼近論、最優(yōu)化理論、非光滑分析、人工神經網絡、醫(yī)學圖像處理、癌癥演化建模等, 并將相關研究成果應用于醫(yī)療和教育大數(shù)據(jù)分析, 開發(fā)具有自主知識產權的醫(yī)療和教育輔助軟件.詳情請見葉頎(Qi Ye)教授個人主頁：http://mlopt.scnu.edu.cn/a/20170209/8.html

甘肅應用數(shù)學中心

甘肅省高校應用數(shù)學與復雜系統(tǒng)省級重點實驗室

萃英學院

yl7703永利官網