机器学习的箭图方法
Quiver representations are a useful tool in diverse areas of algebra and geometry. Recently, they have furthermore been used to describe and analyze neural networks. I will introduce quivers, their representations, and a range of applications, including to the theory of machine learning.
讲师
日期
2022年09月13日 至 10月27日
网站
修课要求
Some representation theory or algebraic geometry would be helpful.
课程大纲
1. Quivers, quiver representations, path algebras, modules;
2. continuous groups, Grassmannians, homogeneous spaces, quiver flag varieties, moduli spaces;
3. neural networks, data flow, activation functions, gradient flow;
4. universal approximation theorems, further topics.
2. continuous groups, Grassmannians, homogeneous spaces, quiver flag varieties, moduli spaces;
3. neural networks, data flow, activation functions, gradient flow;
4. universal approximation theorems, further topics.
听众
Graduate
视频公开
公开
笔记公开
公开
语言
英文
讲师介绍
2018年加入YMSC。自2021起担任YMSC的副教授以及BIMSA的兼职副教授。他的研究重点是几何,特别是利用同调代数和范畴论的工具,将物理学和非交换代数中的思想用于代数簇的研究。他曾就读于剑桥大学,在伦敦帝国理工学院获得博士学位,并在英国爱丁堡大学担任博士后。2014-2018年,他在东京大学Kavli IPMU担任研究员,现在是该校的访问副研究员。他的论文发表在Communications in Mathematical Physics,Duke Mathematical Journal等期刊上。他入选了海外高层次人才计划,并获得了日本科学促进会青年科学家奖。