Acceleration of Large Transformer Model Training by Sensitivity-Based Layer Dropping.

Yujie Zeng Wenlong He Ihor Vasyltsov Jiali Pang Lin Chen

Published in: AAAI (2023)

Keyphrases

computational model
prior knowledge
statistical model
probability distribution
em algorithm
mathematical model
simulation model
supervised learning
experimental data
theoretical analysis
multi layer
neural network model
training samples
feature selection
training set
image sequences
decision trees