google/tangent
Source-to-Source Debuggable Derivatives in Pure Python
Efficiently computes derivatives of NumPy code.
Source-to-Source Debuggable Derivatives in Pure Python
:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Solve automatic numerical differentiation problems in one or more variables.
AutoML library for deep learning
Fast and Accurate ML in 3 Lines of Code
3 captures since 2026-05-22