An Observation on Generalization

Name: An Observation on Generalization
Description: 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.

Simons Institute for the Theory of Computing

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.

Cited in discussions of learning as compression and of why neural networks generalize.

3 Hacker News mentions · 2023–2026

Topics

Machine learning & deep learning
LLMs & generative AI
Information theory & signal processing

Watch on YouTube

Explore more videos