Oct 28 2021

The Ill-defined Problem of Maximum Likelihood Estimation
Why we use maximum likelihood for density estimation, when it breaks down (especially on real-world data), and what can be done about it.

May 25 2018

Variational Autoencoder
Training a VAE on MNIST from scratch using Keras.

Jul 21 2017

Restricted Boltzmann Machine and Contrastive Divergence
RBM training with CD from scratch on MNIST data.