PickVidsAn Observation on Generalization
Why it was recommended
Ilya argues that the reason why neural networks generalize -- why they work at all -- is because they are effectively finding a simple description
Referencejawarner · Original
What it covers
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. It is for someone who wants the derivation, proof, or implementation detail.
Video details
- Channel
- Simons Institute for the Theory of Computing
- Length
- 57 min 21 sec
- Year
- 2023
More in this topic
- 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)