Diff-Glat: Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning.

Lihua Qian Mingxuan Wang Yang Liu Hao Zhou

Published in: CoRR (2022)

Keyphrases

learning algorithm
learning process
active learning
learning systems
reinforcement learning
supervised learning
learning scheme
data sets
multiscale
fuzzy logic
learning problems
image processing
prior knowledge
knowledge acquisition
incremental learning
hidden state