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-vector multiplication two ways: the row picture and the column picture

taught

Taught in

Requires

Nothing — this is foundational.

Required by

Local knowledge map

Local knowledge map

Backpropagation in matrix form Feature creation: polynomial, interaction, binning,… Features, samples, and training/validation/test splits Forward propagation NumPy's broadcasting rule, mechanically PCA: variance maximization and reconstruction error Simple linear regression and least squares The dihedral group Dₙ The maximal margin classifier Vector-valued solutions and the vector Wronskian Why multiplication is defined that way: composition Writing a custom nn.Module, including a custom loss Data as vectors and matrices Matrix multiplication 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… A NumPy array is a vector or matrix, in code A PyTorch tensor is the same array, in a third container A linear model is a weighted sum plus a bias Matrices: notation, shape, and special forms The dot product What a differential equation is (order, solutions, general vs…

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.