Completed
summary of what we learned, how to go towards modern neural nets
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Intro to Neural Networks and Backpropagation - Building Micrograd
Automatically move to the next video in the Classroom when playback concludes
- 1 intro
- 2 micrograd overview
- 3 derivative of a simple function with one input
- 4 derivative of a function with multiple inputs
- 5 starting the core Value object of micrograd and its visualization
- 6 manual backpropagation example #1: simple expression
- 7 preview of a single optimization step
- 8 manual backpropagation example #2: a neuron
- 9 implementing the backward function for each operation
- 10 implementing the backward function for a whole expression graph
- 11 fixing a backprop bug when one node is used multiple times
- 12 breaking up a tanh, exercising with more operations
- 13 doing the same thing but in PyTorch: comparison
- 14 building out a neural net library multi-layer perceptron in micrograd
- 15 creating a tiny dataset, writing the loss function
- 16 collecting all of the parameters of the neural net
- 17 doing gradient descent optimization manually, training the network
- 18 summary of what we learned, how to go towards modern neural nets
- 19 walkthrough of the full code of micrograd on github
- 20 real stuff: diving into PyTorch, finding their backward pass for tanh
- 21 conclusion
- 22 outtakes :
