Supplementary material for the publication "NN architectures for VS classification"

The dataset provided here is part of the study paper on neural architectures for variable stars classification (Jamal and Bloom, 2020). The dataset is constructed from the public photometry variable stars database of the MACHO survey (Alcock et al., 1996). Included in the dataset are phase-folded light-curves, as well as the times-series, for 17603 variable stars from the public MACHO database. Please refer to the readME file for further description. This dataset is provided for research-use only under the non-commercial license on Zenodo.<br> For any use of this dataset, please make sure to cite the MACHO collaboration (see credits hereafter) and the following references. <br> <strong>** REFERENCES **</strong> Alcock, C., Allsman, R. A., Axelrod, T. S., et al. 1996, ApJ, 461, 84, doi:10.1086/177039 MACHO public database: http://macho.nci.org.au/ Jamal, S., &amp; Bloom, J. S., 2020, arXiv:2003.08618 <br> <strong>** ACKNOWLEDGMENTS </strong><em>(on the use of the public MACHO VS data)</em><strong> **</strong><br> "This work utilizes public domain data obtained by the MACHO Project, jointly funded by the US Department of Energy through the University of California, Lawrence Livermore National Laboratory under contract No. W-7405-Eng-48, by the National Science Foundation through the Center for Particle Astrophysics of the University of California under cooperative agreement AST-8809616, and by the Mount Stromlo and Siding Spring Observatory, part of the Australian National University."