ConceptMathematics
Automatic differentiation
A set of techniques to numerically evaluate the derivative of a function specified by a computer program.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
4Each in their own terms, from the easiest level.
Pieter Abbeel
Software techniques that automatically compute derivatives of functions by caching information during a forward pass and performing a backward pass.Gilbert Strang
A set of techniques to evaluate the derivative of a function specified by a computer program, underlying backpropagation.Pablo Rodriguez-Fernandez
A set of techniques to evaluate the derivative of a computer program accurately and efficiently by accumulating derivatives through primitive operations.
Lectures that assume it
5Connections
19The lectures that define it or assume it, and the concepts next to it.
Concepts10
Lectures9
- Machine Learning: Optimization and Neural Networks
- Predicting Core Performances in Tokamaks with Surrogate Optimization
- Backpropagation: Finding Partial Derivatives
- Alan Edelman on the Julia Language for High-Performance Computing
- Building makemore Part 4: Becoming a Backprop Ninja (Manual Tensor Gradients)
- Computer-Assisted Proofs in Fluid PDEs using Interval Arithmetic