Checkpoint: constrained optimization and descent
This lesson includes a 10-question quiz.
About this course
Part of Mathematics for Machine Learning 2: Calculus and Optimization for Training Models — Learn the calculus and optimization machinery that trains models: derive gradients by hand, understand convexity and learning rates, and verify every result numerically.
- Level
- Intermediate
- Goal
- Fundamentals
- Language
- English
- Focus
- gradients and chain rule convexity gradient descent matrix calculus constrained optimization
- Prior knowledge
- Vectors, matrices and matrix multiplication, Comfort reading function notation, Basic Python
- Practice
- Worked examples
- Time
- ~4.9h
- Voice
- a numerical-optimization researcher who derives each gradient by hand and then proves it correct with a numeric check in code
- Not covered
- Linear algebra fundamentals, Probability theory, Deep learning architectures
This lesson is premium content. Sign in and purchase the course to view the full content. Sign in