PickVidsThe Simple Essence of Automatic Differentiation - Conal Elliott
推荐理由
There's a talk that Conal gives that makes the paper a bit more accessible
说明
这是2018年由Microsoft Research发布的一部演讲，主题归在Machine learning & deep learning。它讲的是automatic differentiation这一支里的具体问题，而不是把整个领域扫一遍。适合想看推导、证明或实现细节的人。内容上可以概括成：Conal Elliott presents his paper on automatic differentiation, deriving a simple, generalized AD algorithm from a natural specification. Varying the representation of derivatives yields forward and reverse mode algorithms that avoid the complexity and statefulness of backpropagation.这些读者给出的理由，核心是：Cited as the more accessible companion to the paper, and as the most interesting treatment of AD via compiling to categories.讲法不绑某一条新闻，过几年仍然可以当材料看。从2018年到2023年，有3位不同的读者在4个不同月份把它推荐出来，其中明确叫别人去看的有1次。适合一次性看完。讲者把一个判断讲透，演示是在给这个判断配例子。如果已经会了基本定义，就把注意力放在它怎么把automatic differentiation变成能跟着复述的例子。
视频信息
- 频道
- Microsoft Research
- 时长
- 1 小时 30 分
- 发布年份
- 2018
同主题更多
- The spelled-out intro to neural networks and backpropagation: building micrograd
- But what is a neural network? | Deep learning chapter 1
- AlphaGo - The Movie | Full award-winning documentary
- Transformers, the tech behind LLMs | Deep Learning Chapter 5
- USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?
- Lecture 1 | Machine Learning (Stanford)