Blog

Technical writeups, explorations, and interactive experiments.

Autoencoders & VAEs

From bottleneck compression to generative models. Ground-up derivations of autoencoders, variational autoencoders, the ELBO, and the reparameterization trick, with interactive MNIST demos.

mlautoencodersvae
May 7, 2026

Weight Initialization

Why random weights need the right scale, and how Xavier and He initialization preserve signal variance through deep networks. Ground-up derivations with interactive demos.

mlneural-networksinitialization
May 6, 2026

Activation Functions

Why neural networks need nonlinearity, and what happens when you pick sigmoid vs ReLU vs GELU. Interactive demos of each function and its gradient.

mlneural-networksactivation-functions
May 4, 2026

Dimensionality Reduction

PCA finds straight lines, t-SNE and UMAP find curves. Interactive demos showing how each method projects high-dimensional data onto 2D.

mldimensionality-reductionpca
May 4, 2026

L1 vs L2 Loss: MAE and MSE

Interactive comparison of L1 and L2 loss functions. Drag outliers around and watch regression lines react differently.

seriesmlloss-functionsregression
April 30, 2026

Lasso vs Ridge: L1 and L2 Regularization

Interactive comparison of L1 and L2 regularization. See why Lasso zeros out weights, Ridge just shrinks them, and how the constraint geometry explains it all.

seriesmlregularizationregression
April 30, 2026

Norms: Measuring Size and Distance

What Lp norms are, why L1 and L2 measure different things, and how the unit ball shape explains everything from Manhattan distance to sparsity.

seriesmllinear-algebranorms
April 30, 2026

From MLE to MAP: L2 Regularization is Bayesian in Disguise

Interactive exploration of MLE, MAP estimation, and the Gaussian prior hiding inside weight decay.

mlbayesianregularization
April 29, 2026

DoMINO: How NVIDIA's Physics Surrogate Works

Interactive architecture explorer for NVIDIA's DoMINO model. Walk through every layer of the pipeline that predicts full aerodynamic flow fields from raw STL geometry in seconds.

mlcfddeep-learning
April 28, 2026

PCA of SDFs

How many principal components does it take to reconstruct a 3D shape from its signed distance field? Interactive rebuild from the ground up.

mlcomputer-graphicspca
April 13, 2026

What is a signed distance field?

The scalar function that quietly underpins most modern 3D ML. Interactive intuition, minimal math.

mlcomputer-graphicssdf
April 13, 2026