Login / Signup
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory.
Wenjie Li
Zhaoyang Zhang
Xinjiang Wang
Ping Luo
Published in:
CoRR (2020)
Keyphrases
</>
long term memory
short term
working memory
short term memory
cognitive load
real time
loss function
cognitive architecture
knowledge base
objective function
focus of attention