Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity.

Lu Yin Shiwei Liu Ajay Jaiswal Souvik Kundu Zhangyang Wang

Published in: CoRR (2023)

Keyphrases

pre trained
training data
training examples
control signals
linear combination
high dimensional
real time
neural network
machine learning
active learning
sparse representation