Overview
Dive into a 43-minute video tutorial on calculus exercises for machine learning, led by Weights & Biases experts Charles Frye and Scott Condron. Explore key concepts like little-o notation, gradients as linear approximations, and gradient descent through hands-on Python exercises using SymPy. Learn to implement and understand crucial mathematical foundations for ML, including checking little-o conditions, creating linear approximations, and applying gradients in optimization. Follow along with provided GitHub resources and complementary materials to deepen your understanding of calculus in the context of machine learning.
Syllabus
- Teaser
- Intro
- Little-o notation
- Checking is_little_o in Python
- Doing math in Python with SymPy
- What does little-o mean?
- Exercise: is_little_o_x
- The gradient is a linear approximation
- Different meanings of "the" gradient
- Gradient of a constant function
- Exercise: Making a linear_approximation
- Gradients and optimization
- Exercise: Gradient descent
- Outro
Taught by
Weights & Biases