Apr.08--“Who am I, where have I been, and where am I going?”
“Who am I, where have I been, and where am I going?”
- Theorems and proof
- The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale’s 18th
- English reviews
We use to denote the end of a proof and to denote the end of a remark.
Deep learning (DL) has demonstrated unparalleled accomplishments in fields ranging from image classification and computer vision (1–3), to voice recognition and automated diagnosis in medicine (4–6), to inverse problems and image reconstruction (7–12).
FIRENETs offer a blend of both stability and accuracy. However, they are by no means the end of the story.
- Code
https://github.com/JingyunLiang/VRT
Paper Reading
- The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale’s 18th
Something about the light-flow, which is a dense distritbuion
下午讲座总结
- 视觉定位
- VSNet
- 多粒度信息
此处注意场景，环境，物体 - 精准光照估计
- 轻量级
Nice finding
https://quotefancy.com/carl-sandburg-quotes
Supplement
inf 是 infimum 的简称，sup 是 supremum 的简称。
sup 的定义：一个集合最小的上界
inf 的定义：一个集合最大的下界
归纳总结
Definition and Assumption in Multi-modal Problem Formulation
归纳一下，相关总结，sensitive似乎和sharpness一样。注意关联和传承关联关系。