PickVidsGradIEEEnt half decent: The hidden power of imprecise lines
推荐理由
A fun example of that (making a neural network using floating point error as a source of non-linearity)
说明
这是2023年由suckerpinch发布的一部讲解，主题归在Machine learning & deep learning。它讲的是floating point nonlinearity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：Tom 7 (suckerpinch) delivers a long, comedic digression on gradient descent and floating-point imprecision. He shows how rounding behavior can supply the nonlinearity needed to build a neural network.这些读者给出的理由，核心是：Cited as a fun, unconventional example of neural networks built from floating point error.讲法不绑某一条新闻，过几年仍然可以当材料看。从2023年到2024年，有1位不同的读者在1个不同月份把它推荐出来，其中明确叫别人去看的有0次。适合用一集把一个概念补上的人。抓住它用的那个图像或类比，比背公式重要。如果已经会了基本定义，就把注意力放在它怎么把floating point nonlinearity变成能跟着复述的例子。
视频信息
- 频道
- suckerpinch
- 时长
- 55 分 2 秒
- 发布年份
- 2023
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)