Login / Signup
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning.
Pan Zhou
Jiashi Feng
Chao Ma
Caiming Xiong
Steven C. H. Hoi
Weinan E
Published in:
CoRR (2020)
Keyphrases
</>
deep learning
unsupervised learning
machine learning
unsupervised feature learning
mental models
restricted boltzmann machine
deep architectures
co occurrence
weakly supervised
deep belief networks
data sets
data mining