1 repo
Awesome GitHub RepositoriesCustom Differentiation Rules
Interfaces for defining manual Jacobian-vector products to override standard differentiation behavior.
Distinguishing note: Focuses on user-defined overrides for differentiation, distinct from automated gradient calculation.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Custom Differentiation Rules. Refine with filters or upvote what's useful.
Awesome Custom Differentiation Rules GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- jax-ml/jax
jax-ml/jax
34,919View on GitHubThis project is a high-performance numerical computing library designed for large-scale scientific and machine learning workloads. It functions as an automatic differentiation framework and a just-in-time compilation engine, transforming high-level Python code into optimized machine instructions. By enforcing pure functional programming patterns and immutable array semantics, the library ensures that mathematical functions remain compatible with automated graph transformations and symbolic differentiation. The platform distinguishes itself through its distributed array computing capabilities,
Overrides standard differentiation behavior by specifying custom Jacobian-vector or vector-Jacobian products.
Pythonjax
