Math for ML / calculus-optimization

Calculus and optimization

Derivatives, gradients, chain rule, SGD, Adam, saddle points, clipping, and unstable learning rates.

shellstatic shell now
Focus
  • gradient descent
  • Adam vs SGD
  • backpropagation
  • gradient clipping
Future feature idea

Gradient descent playground with learning rate, momentum, Adam, clipping, and saddle points.

Self-check
  1. What is the core job of "Calculus and optimization"?
  2. Which common mistake would break a production implementation of this topic?
  3. Which inputs or limits must be validated before the interactive feature ships?
  4. What is the smallest test that proves the future implementation behaves correctly?
  5. When does this module really need backend compute, and when is a UI simulation enough?
Implementation notes
  • Start with one focused feature, not a full course inside one page.
  • All public inputs must be typed, bounded, and covered by reject-case tests.
  • If a model, dataset, or job is added, document source, license, limits, and fallback.
  • The interaction must explain the topic rather than serve as decoration.