Jump to Conclusions: Short-Cutting Transformers with Linear Transformations.

Alexander Yom Din Taelin Karidi Leshem Choshen Mor Geva

Published in: LREC/COLING (2024)

Keyphrases

linear transformations
linear transformation
linear model
locally optimal
parameter space
markov chain
pairwise
least squares
image sequences
feature extraction
object recognition
active learning
semi supervised
frequency domain