Completed
Chain rule doesn't care about order
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Differentiable Functional Programming
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Parametrised functions Supervised learning Gradient descent
- 3 Calculate gradient for current parameters
- 4 Deep learning is supervised learning of parameterised functions by gradient descent
- 5 Tensor multiplication and non-linearity
- 6 Algorithms for calculating gradients
- 7 Composition of Derivatives
- 8 Mathematician's approach
- 9 Symbolic differentiation
- 10 Programmer's approach
- 11 Automatic differentiation approach
- 12 Calculate with dual numbers
- 13 Forward-mode scales in the size of the input dimension
- 14 Chain rule doesn't care about order
- 15 Tensor dimensions must agree
- 16 Solution: expressive type systems
- 17 Need compilation (to GPU) for performance
