machine-learning

Optimization vocabulary for ML: gradient descent and constraints

taught

Stochastic gradient descent, convexity, and Lagrange multipliers, restated as the machinery every model-fitting procedure in this course calls "training."

Taught in

Gradient descent and optimization, for ML
Modern Machine Learning

Requires

stochastic-gradient-descent required
convex-functions-and-epigraphs required
lagrange-multipliers required

Required by

Backpropagation: the chain rule you already know required
Models, training, inference, and prediction required
Scaling and standardization required
Simple linear regression and least squares required
The maximal margin classifier required

Local knowledge map

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.