Skip to content

Deep learning frameworks

Autodiff, the computational graph, the training loop and device placement transfer across all of them. Eager vs traced execution splits them, and JAX’s functional purity transfers to neither of the others.

Layer 24 entities0 started
  • pytorch

    Not started. Becomes a package with its own syllabus once it begins.

    candidate
  • tensorflow

    Not started. Becomes a package with its own syllabus once it begins.

    candidate
  • keras

    Not started. Becomes a package with its own syllabus once it begins.

    candidate
  • jax

    Not started. Becomes a package with its own syllabus once it begins.

    candidate