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

deep-learning

A linear model is a weighted sum plus a bias

taught

Taught in

Requires

Required by

Local knowledge map

Local knowledge map

A loss function -- one number for how wrong Defining and calling a Python function Importing a package in Python Minibatch and stochastic gradient descent Python if/else as the step activation Python lists as feature vectors, indexed from 0 Writing a custom nn.Module, including a custom loss Fitting a line with gradient descent Numbers and variables in Python Reading a weight, sign and size per unit Residual and squared error for one example The bias shifts every output nn.Linear is Wx + b A linear model is a weighted sum plus a bias A PyTorch tensor is the same array, in a third container Gradient descent with more than one parameter Matrix-vector multiplication two ways: the row picture… Mean squared error Plugging numbers into a formula, in the right order Features, turning facts into numbers with units What a prediction is (input, output, model)

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.