Tribuo is a library for Machine Learning, written in Java, which supports classification, regression, clustering, anomaly detection, along with deep learning support via TensorFlow and ONNX. Tribuo has a strong focus on model metadata & tracking through it’s provenance system, supports loading third party models including those trained in Python packages like scikit-learn, and provides a variety of ML algorithms implemented in Java. Jupyter notebook based tutorials (statically hosted on the website - https://tribuo.org/learn/4.0/tutorials/, and the notebooks themselves on github - https://github.com/oracle/tribuo/tree/main/tutorials).

I'm the lead developer on Tribuo, happy to answer any questions. The announcement blogpost goes into more detail about why we built it and where it fits into the ML ecosystem - https://blogs.oracle.com/datascience/tribuo-java-machine-lea...