Completed
2:00 Why Analytical methods are infeasible
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Evolution of Back Propagation: Who Invented It?
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Why perceptron convergence learning could no longer be used
- 2 2:00 Why Analytical methods are infeasible
- 3 4:00 How numerical methods like gradient descent are feasible
- 4 7:00 Gradient vector and direction of steepest ascent
- 5 13:58 An efficient way to compute gradients
- 6 17:32 What is "backward" in back propagation and why
- 7 18:48 How this efficient gradient compute method is used in neural networks
- 8 20:08 Who invented backprop
- 9 23:22 Quiz Time
- 10 24:37 Summary
