Synthetic Data with Gumbel-Softmax Activations

Hands-on high quality categorical data synthesis

In classification a central problem is how to effectively learn from discrete data formats (categorical or ordinal features). Most datasets present us with this problem so I guess it is fair to say that almost all data scientists have faced this at some point (right?).

Despite the existence of different techniques that may mitigate it, this is an issue that involves compromises to get past. A choice …

activation-functions categorical-data data data-synthesis machine learning synthetic data