Login / Signup
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.
Jaehoon Lee
Lechao Xiao
Samuel S. Schoenholz
Yasaman Bahri
Jascha Sohl-Dickstein
Jeffrey Pennington
Published in:
CoRR (2019)
Keyphrases
</>
linear models
neural network
variable selection
linear regression
linear model
pattern recognition
gaussian processes
learning rules
nonlinear models
data analysis
moving objects
high dimensional
model selection
sample size