Topics · Concept

Neural networks

Layers of weights that learn a function from examples: architectures, activations, quantisation, and running them where the data is.

Within
Machine learning
Pages
2
On the map 2 pages and the topics around it
Tap a dot to select it, tap again to open it.

Open in the full map →

  1. 2026

  2. noteA self-fulfilling prophecy

    Karen Hao says scaling laws are like Moore's Law: not a law of nature but a self-fulfilling prophecy. She is half right, and the half matters.

    Neural networksSemiconductorsForecastingHistory of technologyTechnology races

  3. noteIntelligence is compression

    Ilya Sutskever's internal slogan at OpenAI: a model that must predict the world has to compress it. I think it is the most useful definition we have.

    IntelligenceLanguageNeural networksMathematics

    Open the full search →