DNDNALYAWAI-native quant labSkip to content
← All notes

Learning systems ·

The Four Realms of Neural Networks

Four lenses on deep learning: PDE solvers, manifold geometry, gauge fields, and quantum-like attention. Each reveals structure the one below cannot express.

Key ideas

  1. 01

    A residual network behaves like a numerical solver for a differential equation, with coefficients learned by gradient descent and boundary conditions set by the prompt.

  2. 02

    Training flattens tangled data manifolds until classes separate, and weights act as a connection on a fiber bundle over the data, so geometry matters more than parameter count.

  3. 03

    Attention works like a measurement whose basis the prompt selects, so AGI should be a small core model with dynamic memory for each person, not one model for everyone.

Read the full essay

Written by Wayland Zhang, founder of Dnalyaw.