Classical Machine Learning
3 entriesToolkits for tabular data and classic algorithms.
Gradient Boosting
2 entriesFast tree-boosting libraries often best on tabular data.
Deep Learning Frameworks
3 entriesFrameworks for neural networks.
06PyTorchAn open source machine learning framework that accelerates the path from research prototyping to production deployment.
07TensorFlowAn end-to-end open source platform for machine learning, with a flexible ecosystem of tools, libraries, and community resources.
08JAXA high-performance array computing library for accelerator-oriented program transformation, offering composable function transforms for large-scale machine learning.
Related Pages
6 entriesRelated directories on this site.
09Machine LearningMachine learning hub.
10Deep Learning FrameworksDeep learning frameworks.
11Python Frameworks for AIPython frameworks for AI.
12Machine Learning LibrariesML libraries across languages.
13Machine Learning Frameworks in JuliaML frameworks in Julia.
14MLOps PlatformsOperationalising machine learning.
Frequently Asked Questions
What is a machine learning framework?
A library that provides algorithms, data handling and training tools so you can build and evaluate models without implementing them from scratch.
scikit-learn or a deep learning framework?
scikit-learn suits classical algorithms on tabular data; PyTorch, TensorFlow and JAX suit neural networks on images, text and audio.
Which library is best for tabular data?
Gradient boosting libraries such as XGBoost and LightGBM often lead on tabular problems.
What if I use R or Julia?
tidymodels covers R; see the Machine Learning Frameworks in Julia page for Julia.
How do I move from training to production?
See the MLOps Platforms and model serving pages.