Watch gradient descent optimize in 3D: pick any coordinate plane, see contour slices update, and track x₁, x₂, x₃, and f over time.
Project a 2D point cloud onto k principal components (k∈{0,1,2}) and reconstruct. Adjust angle and anisotropy; watch retained variance and reconstruction error.
Two optimizers descend the same 2D bowl. Watch paths and values per step.
Simple examples showing how to minimise or maximize functions using gradient descent
A simple, easy to understand and step by step tutorial on Q-Learning using a simple example.
