The paper establishes rigorous theorems proving the Frequency Principle holds for general deep neural networks at initial, intermediate, and final training stages.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Theory of the Frequency Principle for General Deep Neural Networks
The paper establishes rigorous theorems proving the Frequency Principle holds for general deep neural networks at initial, intermediate, and final training stages.