Learn practical skills, build real-world projects, and advance your career
Created 5 years ago
Note: This is a mirror of the official fast.ai notebook for the DSNet Study Group, please refer the official course repo for the latest notebooks.
import torchWhy you need a good init
To understand why initialization is important in a neural net, we'll focus on the basic operation you have there: matrix multiplications. So let's just take a vector x, and a matrix a initiliazed randomly, then multiply them 100 times (as if we had 100 layers).