Login / Signup
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent.
William Merrill
Vivek Ramanujan
Yoav Goldberg
Roy Schwartz
Noah A. Smith
Published in:
EMNLP (1) (2021)
Keyphrases
</>
inductive bias
training examples
objective function
training set
supervised learning
inductive learning
decision trees
machine learning
prior knowledge
training samples
pac learning
active learning
small number
learning algorithm
semi supervised
model selection