Cite
Notes
Only stored in your browser.
Attribution
A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
arXiv 2018
Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates
arXiv 2017
Cyclical Learning Rates for Training Neural Networks
arXiv 2015
from 3 papers
Nicholay Topin