On Initializing Transformers with Pre-trained Embeddings.

Ha Young Kim Niranjan Balasubramanian Byungkon Kang

Published in: CoRR (2024)

Keyphrases

pre trained
training data
low dimensional
training examples
manifold learning
dimensionality reduction
high dimensional data
control signals
computer vision
wide range
data sets
learning algorithm
high dimensional
decision trees
viewpoint
prior knowledge