Active Learning: Encoder-Decoder-Outlayer and Vector Space Diversification Sampling

Active Learning: Encoder-Decoder-Outlayer and Vector Space Diversification Sampling

This study introduces a training pipeline comprising two components: the Encoder-Decoder-Outlayer framework and the Vector Space Diversification Sampling method. This framework efficiently separates the pre-training and fine-tuning stages, while the sampling method employs pivot nodes to divide the...

Full description

Bibliographic Details
Main Authors: Hongyi Zeng, Fanyi Kong
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Mathematics
Subjects:
neural network
training pipeline
Encoder-Decoder-Outlayer framework
Vector Space Diversification Sampling method
human labeling
GPU memory
Online Access:https://www.mdpi.com/2227-7390/11/13/2819

Internet

https://www.mdpi.com/2227-7390/11/13/2819

Similar Items