Automated ML

Automated ML, or AutoML, refers to methods and processes that make machine learning more accessible, improve the efficiency of ML systems, and accelerate AI application development. It aims to automate manual tasks typically performed by human ML experts.

AutoML is designed for users ranging from non-ML experts to experienced researchers and developers. It addresses the demand for off-the-shelf machine learning methods that can be used easily without deep technical expertise.

AutoML covers research areas such as hyperparameter optimization, neural architecture search, meta-learning, explainable AutoML, and dynamic algorithm configuration. It also includes tools for reinforcement learning, healthcare, and efficient ML systems.

AutoML provides open-source tools like SMAC3, Auto-PyTorch, NASLib, and others for tasks such as hyperparameter optimization, neural architecture search, and performance prediction. These tools are developed by academic research groups at the University of Freiburg, Leibniz University Hannover, and the University of Tübingen.

Users can explore AutoML through its open-source tools, research publications, tutorials, and benchmark resources available on the website. The platform also offers educational materials like MOOCs and workshops to help users learn and apply AutoML techniques.

Yes, AutoML provides educational resources including MOOCs, tutorials, invited talks, workshops, and AutoML schools. These resources are designed to help users understand and apply AutoML methods in their projects.