Optimal transmission theory course information:
On Saturday, October 17th, 9:00-10:30pm, Beijing time, and on Sunday, October 18th, 9:00-10:30pm, Beijing time, we will continue to explain the optimal transmission course. The content is Minkowksi and Alexandrov theorem, including Convex Hull algorithm, Brunn-Minkowski inequality, fixed point theorem, domain invariance theorem, Alexandrov theorem, Pogorelov theorem proof, etc.
Assign the first assignment: 3D convex hull algorithm
Welcome to:
zoom ID：578 945 9691
Station B: online.conformalgeometry.org
@everyone
The 16th Annual Conference on Theory and Applications of Models of Computation, Sunday morning, 10/18/2020, Beijing time, 9:00-9:50
Keynote Speech： A Geometric Understanding of Deep Learning By Xianfeng Gu
Everyone is welcomed to join.
The conference website:
https://tamc2020.csu.edu.cn/html/Program.html
Past courses on optimal transport theory and computational conformal geometry can be found on Station B:
https://space.bilibili.com/446605493/
Yesterday's Harvard speech can be seen on Tencent Video:
Introduction from:
https://cmsa.fas.harvard.edu/literature-lecture-series/
Content comes from:
https://www.youtube.com/watch?v=Olmsu6pg0lM&feature=push-sd&attr_tag=3czPynnwdwfl5VIn%3A6
Harry Shum (Tsinghua University)
Title: From Deep Learning to Deep Understanding
Abstract: In this talk I will discuss a couple of research directions for robust AI beyond deep neural networks. The first is the need to understand what we are learning, by shifting the focus from targeting effects to understanding causes. The second is the need for a hybrid neural/symbolic approach that leverages both commonsense knowledge and massive amount of data. Specifically, as an example, I will present some latest work at Microsoft Research on building a pre-trained grounded text generator for task-oriented dialog. It is a hybrid architecture that employs a large-scale Transformer-based deep learning model, and symbol manipulation modules such as business databases, knowledge graphs and commonsense rules. Unlike GPT or similar language models learnt from data, it is a multi-turn decision making system which takes user input, updates the belief state, retrieved from the database via symbolic reasoning, and decides how to complete the task with grounded response.
Machine-translated from the Chinese original 最优传输理论课程信息：哈佛CMSA: From Deep Learning to Deep Understanding (published 2020-10-16). WeChat original ↗