Gradient Information Analysis of ReLU Networks
ResNets are one of the most useful neural network architectures. They have been used to great success, particularly in applications like computer vision. However, they are highly nonlinear and non-convex, which leads to difficulty in trying to train them as well as difficulty in trying to analyze...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Princeton University Senior Theses |
Language: | English |
Published: |
2019
|
Online Access: | http://arks.princeton.edu/ark:/88435/dsp018k71nk95g |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|