PickVidsAn Observation on Generalization
推荐理由
Ilya argues that the reason why neural networks generalize -- why they work at all -- is because they are effectively finding a simple description
说明
这是2023年由Simons Institute for the Theory of Computing发布的一部演讲，主题归在Machine learning & deep learning。它讲的是generalization and compression in ml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：Ilya Sutskever gives a Simons Institute talk on why neural networks generalize, framing learning as finding short descriptions, like compression. It was part of the Large Language Models and Transformers program.这些读者给出的理由，核心是：Cited in discussions of learning as compression and of why neural networks generalize.讲法不绑某一条新闻，过几年仍然可以当材料看。从2023年到2026年，有0位不同的读者在0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generalization and compression in ml变成能跟着复述的例子。
视频信息
- 频道
- Simons Institute for the Theory of Computing
- 时长
- 57 分 21 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)