Login / Signup
Intelligent Learning Rate Distribution to Reduce Catastrophic Forgetting in Transformers.
Philip Kenneweg
Alexander Schulz
Sarah Schröder
Barbara Hammer
Published in:
IDEAL (2022)
Keyphrases
</>
learning rate
learning algorithm
convergence rate
error function
rapid convergence
adaptive learning rate
hidden layer
multilayer neural networks
convergence speed
natural gradient
training algorithm
bp neural network algorithm
evolutionary algorithm
weight vector
uniform convergence