Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

linear-algebra

Matrix multiplication

taught

Taught in

Requires

Required by

Local knowledge map

Local knowledge map

Autoencoders Automatic differentiation Computational graphs Dₙ as a subgroup of Sₙ Linear regression as a one-layer network Loss as the training signal Molecular symmetry and point groups Motivating group actions: groups that move things Necklace and bracelet counting Properties, and why AB does not equal BA Rotations and reflections as generators of Dₙ Sequential data and the autoregressive idea Symmetry groups of regular polygons, in general Training versus inference Why a network needs a fast way to find every weight's gradient Backpropagation in matrix form Forward propagation The dihedral group Dₙ Why multiplication is defined that way: composition Matrix multiplication Backpropagation Data as vectors and matrices Generators of a group Layers and parameters Symmetries of a regular n-gon The batch dimension and broadcasting, as engineering convention Writing a system in matrix form nn.Linear is Wx + b np.dot and @ compute the dot product and the matrix product Matrix-vector multiplication two ways: the row picture…

Click to expand

Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.