Login / Signup
M-CTRL: A Continual Representation Learning Framework with Slowly Improving Past Pre-Trained Model.
Jin-Seong Choi
Jae-Hong Lee
Chae-Won Lee
Joon-Hyuk Chang
Published in:
ICASSP (2023)
Keyphrases
</>
prior knowledge
probabilistic model
neural network
reinforcement learning
statistical model
pre trained
data sets
machine learning
learning algorithm
bayesian networks
viewpoint
learning process
active learning
unsupervised learning