PickVidsConnections between physics and deep learning
推荐理由
physical data tends to have symmetries, and these symmetries make descriptions of the data very compressible into relatively small neural circuits
强烈推荐tedsanders · 原文
说明
这是2016年由MITCBMM发布的一部演讲，主题归在Machine learning & deep learning。它讲的是physics and deep learning这一支里的具体问题，而不是把整个领域扫一遍。适合已经能看懂基本术语、想继续往下走的人。内容上可以概括成：Max Tegmark's MIT CBMM talk on why deep learning works so well. He argues that the laws of physics and the symmetries in physical data make it compressible into small neural networks, tying physics to network structure.这些读者给出的理由，核心是：HN recommends it as a clear argument for why deep and cheap learning succeeds, often alongside the associated paper.讲法不绑某一条新闻，过几年仍然可以当材料看。从2016年到2026年，有3位不同的读者在3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physics and deep learning变成能跟着复述的例子。
视频信息
- 频道
- MITCBMM
- 时长
- 51 分 46 秒
- 发布年份
- 2016
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)