Deep learning theory
1 min readMar 7, 2020
Hongyi li gave a pretty good tutorial on deep learning.
Video link
He mentioned some papers for the deep learning theory. Hope it is helpful to have a better understanding about why DL works.
On the Expressive Power of Deep Neural Networks.
“Key findings: (1) The complexity of the computed function grows exponentially with depth. (2) All weights are not equal (initial layers matter more). (3) Trajectory Regularization works like Batch Normalization.”
from a comment of the video.
