ML Visualization

The Learning Path

A guided route through the visualizations, ordered the way a thoughtful course would teach them. Completely optional — think of it as a suggested reading order, not a locked curriculum.

Stage 1 of 5
Stage 1 — Foundations
Start by fitting a line and meeting the ideas of error and gradient descent.
Stage 2 of 5
Stage 2 — Classification
Move from predicting numbers to predicting categories.
- Logistic Regression
  Predict class probabilities with an S-shaped curve.
  ClassificationBeginner⚡
- K-Nearest Neighbors
  Classify by majority vote of nearest neighbors.
  ClassificationBeginner⚡
Stage 3 of 5
Stage 3 — Making models generalize
Find structure without labels, and learn why models fail and how to evaluate them honestly.
- K-Means Clustering
  Cluster by iterating assign-to-nearest-center then move-center.
  Unsupervised & Dim. ReductionBeginner⚡
- Cross-Validation
  Rotate the holdout set across k folds for a stable estimate.
  Data Prep & Model EvaluationIntermediate⚡
Stage 4 of 5
Stage 4 — Neural networks
Assemble simple units into networks that learn features.
- The Perceptron
  The original learning neuron: a linear threshold unit.
  Neural NetworksIntermediate⚡
- Backpropagation
  Propagate error gradients backward to update every weight.
  Neural NetworksAdvanced⚡
Stage 5 of 5
Stage 5 — Deep learning
The architectures behind modern AI — on the roadmap, beyond this site’s current classical-ML focus.
Deep learning explainers (CNNs, RNNs, Transformers) are planned for a future release. This site currently focuses on classical machine learning.