TensorFlow
An end-to-end open-source platform for machine learning. It has a flexible architecture that allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device.
PyTorch
An open-source machine learning framework that accelerates the path from research prototyping to production deployment. It offers great flexibility and is popular in the research community.
Keras
A high-level, user-friendly API that runs on top of TensorFlow, Theano, or CNTK. It focuses on enabling fast experimentation and is known for its ease of use.
XGBoost
An optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It is widely used for tabular data and has won many Kaggle competitions.
Scikit-learn
A free software machine learning library for the Python programming language. It features various classification, regression, clustering algorithms, and has an extensive set of tools for model selection and preprocessing.
JAX
From Google, JAX combines automatic differentiation (autodiff) with XLA (Accelerated Linear Algebra) for high performance on accelerators like GPUs and TPUs. It's gaining traction for its speed and composability.