Interactive Machine Learning Demonstrations

Welcome to our collection of interactive machine learning demos. Each demonstration allows you to experiment with different algorithms and parameters to build intuition about how they work.

Linear Regression

Explore how linear regression finds the best line through data points. Adjust parameters and see how the line changes in real-time.

Regularisation

Experiment with polynomial basis functions and observe how model complexity affects overfitting. Control which polynomial terms to include.

1D Classification

Learn binary classification with a toggle to see the effect of sigmoid activation. Compare linear and sigmoid decision boundaries.

2D Classification

Explore binary classification in 2D space with linear decision boundaries. See how the boundary separates different classes across two dimensions.

Neural Networks

Build intuition about neural networks by interactively designing architectures, adjusting weights, and watching data flow through layers.

Backpropagation

Visualize how gradients flow backwards through neural networks. Watch weights update step-by-step during optimization.

Convolution & Pooling

Learn the fundamental operations of CNNs through interactive convolution and pooling visualizations. Design custom filters and see their effects.

8

CNN Architecture

Explore a complete convolutional neural network for handwritten digit recognition. See how CNNs learn hierarchical features through training.

1
2
3
4
RNN

Recurrent Neural Networks

Discover how RNNs process sequential data step-by-step. Visualize hidden state evolution and understand the core mechanics of recurrent processing.

Q
K
V
The
cat
sat

Attention Mechanism

Explore how attention mechanisms work through Q, K, V computations and dot-product attention. Visualize how tokens attend to each other in sequence processing.

K-Means Clustering

Interactive clustering demonstration with step-by-step k-means algorithm visualization. Add your own points and watch how centroids move to minimize within-cluster distances.

0.0
0.4
0.5
ε-greedy

Multi-Armed Bandit

Explore the exploration vs exploitation tradeoff with interactive slot machines. Watch the epsilon-greedy algorithm learn optimal strategies through trial and reward.