Login / Signup
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn.
Emmanuel Abbe
Elisabetta Cornacchia
Jan Hazla
Christopher Marquis
Published in:
ICML (2022)
Keyphrases
</>
neural network
learning rules
artificial neural networks
loss function
objective function
cost function
fuzzy logic
back propagation
dynamic time warping
image segmentation
neural network model
feed forward
training algorithm
network architecture