The Gumbel-Softmax Distribution

Why Is This Hard?

The Reparameterization Trick

The Gumbel-Max Trick

Bringing It All Together

References:

--

--

--

PhD student in Mechanical Engineering (personal blog: https://sassafras13.github.io/)

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Software Optimization for deploying AI at the edge

Teachable Machine Tutorial: Bananameter

Holding a ripe banana up to the webcam, and recording frames to the “Ripe” class

Difference between Data Science and Machine Learning

LASSO Increases the Interpretability and Accuracy of Linear Models

Lasso at the Rodeo

The Four Maturity Levels of Automated Machine Learning: Towards Domain Specific AutoML

Summary on a Neural Language Model

Tuning and Training Machine Learning Models Using PySpark on Cloud Dataproc

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Emma Benjaminson

Emma Benjaminson

PhD student in Mechanical Engineering (personal blog: https://sassafras13.github.io/)

More from Medium

Linear Regression and Gradient Descent in NumPy

Flappy Bird Beats Itself Using NEAT

DIFFERENT ACTIVATION FUNCTIONS

Hand drawn sketch classification by retraining ResNet50 with transfer learning