v1.0.3

Summary

Expose training parameters from scikit-learn in built-in models and add new advanced examples.

Links

Docker Image: zamafhe/concrete-ml:v1.0.3
pip: https://pypi.org/project/concrete-ml/1.0.3
Documentation: https://docs.zama.ai/concrete-ml

v1.0.3

Feature

• Support multi-input QM with inputs of different shapes (6e1315f)
• Add a function to build a quantized module from a model (34e5f68)
• Expose scikit-learn training attributes in built-in models (37ab8c0)
• Add serialization to QNN models (33312a8)

Documentation

• Add example notebook on LinearSVR (f42f0e6)
• Add svm classifier tutorial (49e13ec)
• Add DecisionTreeRegressor to advanced_examples (148e626)
• Add regressor comparison tutorial (6c7cbf7)