Variational Autoencoder Theory
Formulation of the VAE objective, neural network architecture design, optimization, and practical uses
Recent posts
Variational Autoencoder Code and Experiments
Detailed walkthrough of a PyTorch VAE implementation trained on MNIST, including visualizations of data generation, reconstruction, and anomaly detection
Latent Variable Models, Expectation Maximization, and Variational Inference
Introduction to latent variable models, derivation of the ELBO, and the relationship with Expectation Maximization
A Quick Primer on KL Divergence
Intuitive introduction to KL divergence, including discussion on its asymmetry
Interesting Details about ROC Curve Calculations
Code-based walkthrough showing how AUC is computed for a simple model trained on a simple dataset