Two-Moon Classification

Train a neural network to classify two interleaving half-moon shapes. Watch the decision boundary evolve in real-time as the network learns.

NK Clustering

Online clustering algorithm with bounded cluster sizes. Watch points stream in one-by-one and get assigned to clusters in real-time.

MNIST with Gradient Norm

Online MNIST training with seeded reproducibility, live train/test curves, per-digit recall, and top gradient-norm samples.

10-Digit Addition Grokking

Train a compact model on 10-digit addition and watch the grokking-style train/test loss transition across curriculum phases.

Autoencoder VisualizationComing Soon

Explore how autoencoders compress and reconstruct data. Visualize the latent space and see how the network learns efficient representations.

Gradient Descent PlaygroundComing Soon

Visualize different optimization algorithms navigating loss landscapes. Compare SGD, Adam, RMSprop, and more on various terrain types.