{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/2"}],"enrichment":{"capability":"Autograd automatically computes derivatives of Python and NumPy code, supporting both reverse-mode (backpropagation) and forward-mode differentiation for gradient-based optimization.","skillfed_tags":["autodiff","gradient-computation","optimization"],"use_cases":["Training neural networks by computing gradients for backpropagation without manual derivative code.","Implementing Bayesian inference methods like HMC or variational inference that require gradients of log-probability functions.","Optimizing functions where analytical gradients are tedious or error-prone to derive by hand.","Computing higher-order derivatives (e.g., Hessians) for second-order optimization methods.","Prototyping machine learning models in pure Python/NumPy with automatic gradient computation."],"what_it_does":"Autograd is a library that automatically computes derivatives of Python and NumPy functions without requiring you to write gradient code by hand. It handles a large subset of Python's features\u2014loops, conditionals, recursion, closures\u2014and can differentiate functions multiple times over. The library supports both reverse-mode differentiation (efficient for scalar-valued functions with many inputs, as in neural networks) and forward-mode differentiation, and these can be composed arbitrarily.\n\nThe main use case is gradient-based optimization: you define a function in NumPy, wrap it with autograd's grad function, and get back a function that computes its gradient. This is particularly useful for training neural networks, Bayesian inference, and other machine learning tasks where you need gradients but don't want to manually implement backpropagation. Autograd provides a thin wrapper around NumPy that tracks operations for differentiation.","worth_installing":"Yes. Autograd is actively maintained, has no known vulnerabilities, installs with low friction, and is permissively licensed. It is a solid choice if you need automatic differentiation for NumPy-based code and prefer a lightweight, pure-Python solution over heavier frameworks."},"id":"autograd","links":{"html":"https://skillfed.io/packages/autograd","md":"https://skillfed.io/packages/autograd.md","pypi":"https://pypi.org/project/autograd/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-07-02","license_spdx":"MIT","license_treatment":"permissive","name":"autograd","python_support":"supports_current","summary":"Efficiently computes derivatives of NumPy code."},"popularity":{"monthly_downloads":5606457,"position":2063,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"1.9.1"}