This year we have been seeing a variety of works introducing techniques for improving Transformers and making them more computational and memory efficient. This recent survey paper highlights some notable ideas like Reformer and Longformer, among others.…

本人现代汉语语法方向博士生，有些事情感到不吐不快，也想避免后来人踩坑。知乎文章不支持匿名，由于可以理解的原因，本文专门注册小号发布。曾经的我，也是个语言学的虔诚朝圣者，心怀对语言学的深爱，选择了读博…

#TransferLearning is one of the most important #AI techniques I don't often recommend PhD Thesis' - @seb_ruder's is exceptional. He's a brilliant writer! Check out this taxonomy / table of contents!!! 👇👇👇 #100DaysOfMLCode #100DaysOfCode https://t.co/3Pwc08NRu0

Background

为了方便广大学者进行研究，我们提供最优传输几何变分法的C++源代码，演示程序和测试数据。这一方法是基于丘成桐先生的理论，应用计算几何算法实现。

My first-class Nuxt.js project

布拉格不止初恋，还有……

不谈量子力学，也无关薛定谔。

How to tune hyperparameters for your machine learning model using Bayesian optimization.

https://www.youtube.com/watch?v=pZkCecwE-xE&t=17sWhat is Causal Inference? A Logical Perspective, 视频播放量 3761、弹幕量 2、点赞数 160、投硬币枚数 44、收藏人数 473、转发人数 27, 视频作者 爱可可-爱生活, 作者简介 新浪微博 @爱可可-爱生活 http://weibo.com/fly51fly，相关视频：《因果的真相》：上天将要降福给你， 如果你是有德性的人或是有来历的人， 常常都是逆着你的习性来的。…

Earley parsers can parse any context-free language, without restriction. This is a tutorial for how to write one.