Getting Up to Speed with SHAP for Model Interpretability
Value proposition, intuition, and analytical breakdown of SHAP
Machine Learning Posts
machine learning
Logistic Regression Deep Dive
Derivation of objective and gradient, visualizing a gradient update
Blog Post Series: From KL Divergence to Variational Autoencoder in PyTorch
Landing page for the blog post series
Variational Autoencoder Theory
Formulation of the VAE objective, neural network architecture design, optimization, and practical uses
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