Greg Michaelson AutoML as it should have always been | JupyterCon 2023

Pipelines: A revolutionary open-source AutoML package that addresses the limitations of existing tools by providing a transparent, flexible, and easy-to-use solution for developing and deploying machine learning models.

Key takeaways
  • Automated machine learning (AutoML) tools have been around for a while, but they have several limitations.
  • AutoML tools often only work on a subset of problems, are opaque, and require users to accept a black box solution.
  • Pipelines is a new open-source package that aims to address these limitations by providing a more transparent and flexible AutoML solution.
  • Pipelines can be used to generate code for training, tuning, and evaluating machine learning models.
  • Pipelines supports supervised learning for regression and classification tasks and includes a variety of models, including elastic net, random forest, decision tree, and gradient boosting.
  • Pipelines can be used to parallelize training and tuning tasks, which can significantly reduce the time it takes to develop and deploy machine learning models.
  • Pipelines is easy to use and can be integrated with Jupyter notebooks and other development environments.
  • Pipelines is still under development, but it has the potential to revolutionize the way that machine learning models are developed and deployed.