There is a newer version of this record available.

Software Open Access

ivis: dimensionality reduction in very large datasets using Siamese Networks

Ignat Drozdov; Benjamin Szubert


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3522018", 
  "title": "ivis: dimensionality reduction in very large datasets using Siamese Networks", 
  "issued": {
    "date-parts": [
      [
        2019, 
        10, 
        29
      ]
    ]
  }, 
  "abstract": "<p>Major features:</p>\n\n<ul>\n\t<li>Support for semi-supervised dimensionality reduction</li>\n\t<li>Switch from using fit_generator to fit for training the Keras model</li>\n\t<li>Address eager execution issues with TF 2.0</li>\n\t<li>User-configurable on-disk-building of Annoy index.</li>\n\t<li>Tidy handling of interrupted multi-thread processes</li>\n</ul>\n\n<p>Minor features:</p>\n\n<ul>\n\t<li>Tests for semi-supervised DR</li>\n\t<li>Improved input validation</li>\n\t<li>Better hyper parameter validation</li>\n\t<li>\n\t<p>Slight changes to default hyperparameters</p>\n\t</li>\n\t<li>\n\t<p>Bug fixes</p>\n\t</li>\n</ul>", 
  "author": [
    {
      "family": "Ignat Drozdov"
    }, 
    {
      "family": "Benjamin Szubert"
    }
  ], 
  "version": "1.6.0", 
  "type": "article", 
  "id": "3522018"
}
298
109
views
downloads
All versions This version
Views 29844
Downloads 1093
Data volume 564.3 MB36.6 MB
Unique views 24643
Unique downloads 223

Share

Cite as