方向：理工
专业：人工智能
适合人群：机器学习,深度学习,人工智能,统计学,数据结构与算法,编程语言
是否可以加论文：是
项目时长及形式：英文
产出：
7周在线小组科研学习+5周论文辅导学习 共125课时
学术报告
优秀学员获主导师Reference Letter
EI/CPCI/Scopus/ProQuest/Crossref/EBSCO或同等级别索引国际会议全文投递与发表（可用于申请）
结业证书
成绩单
项目介绍：
本项目为学生提供在监督学习环境中所需的现代数学工具。我们将重点分析和设计正则化方法以及一阶优化方法，包括随机梯度下降法，并介绍统计学理论中的主要思想。学生将在项目结束时，提交项目研究报告，进行成果展示。
Machine Learning (ML) and Artificial Intelligence (AI) are the infrastructures on which our society will rely in the future. Given the vast growth of these fields, however, an increasing proportion of data scientists are seen to rely on a “black-box” approach to ML and AI, applying computational techniques without having a strong critical understanding of their properties. This approach is dangerous for society as a whole. This course aims to fill this gap, providing students with the modern mathematical tools needed to understand ML and AI in the setting of supervised learning (classification and regression). In particular, we will focus on the analysis and design of regularization methods and first-order optimization methods (e.g. stochastic gradient descent), and introduce the main ideas in statistical learning theory.
个性化研究课题参考 Suggested Research Fields
MSE与MAE对机器学习性能优化的作用比较 Comparison of the Effects of MSE and MAE on Machine Learning Performance Optimization
机器学习随机优化方法的个体收敛性研究 Individual Convergence of Stochastic Optimization Methods in Machine Learning
高维因子模型及其在统计机器学习中的应用 High-dimensional Factor Model and Its Application in Statistical Machine Learning
更多留学问题欢迎咨询晨晟留学之家，电话(同微信) 18071732056