Neural Tangents
latest

Public API:

  • nt.stax – infinite NNGP and NTK
  • nt.empirical – finite NNGP and NTK
  • nt.predict – inference w/ NNGP & NTK
  • nt.batch – using multiple devices
  • nt.monte_carlo_kernel_fn - MC Sampling

Internal:

  • nt.experimental – prototypes
  • Kernel dataclass
  • Typing

Colab Examples:

  • Cookbook
  • Weight Space Linearization
  • Function Space Linearization
  • Neural Network Phase Diagram
  • Performance Benchmarks
  • Finite Width NTK

Papers:

  • Neural Tangents: Fast and Easy Infinite Neural Networks in Python
  • Fast Finite Width Neural Tangent Kernel
  • Infinite attention: NNGP and NTK for deep attention networks
  • On the infinite width limit of neural networks with a standard parameterization
  • Fast Neural Kernel Embeddings for General Activations

Other Resources:

  • Neural Tangents Video
  • Finite Width NTK Video
  • Wikipedia
  • GitHub
Neural Tangents
  • Overview: module code

All modules for which code is available

  • neural_tangents._src.batching
  • neural_tangents._src.empirical
  • neural_tangents._src.monte_carlo
  • neural_tangents._src.predict
  • neural_tangents._src.stax.branching
  • neural_tangents._src.stax.combinators
  • neural_tangents._src.stax.elementwise
  • neural_tangents._src.stax.linear
  • neural_tangents._src.stax.requirements
  • neural_tangents._src.utils.kernel
  • neural_tangents._src.utils.typing
  • neural_tangents.experimental.empirical_tf.empirical
  • typing

© Copyright 2021, Google LLC.. Revision 9cfdc287.

Built with Sphinx using a theme provided by Read the Docs.
Read the Docs v: latest
Versions
latest
Downloads
html
On Read the Docs
Project Home
Builds