Python implementation of the Support Vector Data Descriptor classifier. Compatible with scikit-learn. The code is written such that it aligns well with the paper by referencing to equation numbers and elaborate comments, i.e. suitable for research.
- Please refer to the test file for an example. A _plot_contour function is provided to visualize the decision boundary on 2D data.
- Python implementation: Arman Naseri Jahfari ([email protected])
- Original Matlab version: Tax, D.M.J., DDtools, the Data Description Toolbox for Matlab
- Original paper: Tax, D. M. J., & Duin, R. P. W. (2004). Support Vector Data Description. Machine Learning, 54(1), 45–66. https://doi.org/10.1023/B:MACH.0000008084.60811.49
If this code was helpful to your research/publication, please refer to it using the following:
@misc{PythonSVDD,
Author = {Naseri Jahfari, A},
Title = {Python implementation of the Support Vector Data Descriptor},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/Armannas/SVDD}},
DOI = {10.5281/ZENODO.5079875},
Month = {July},
Year = {2021}}
* Initial Release
This project is licensed under the [MIT] License.