Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks.

Justin Werfel Xiaohui Xie H. Sebastian Seung

Published in: NIPS (2003)

Keyphrases

feed forward
learning curves
stochastic gradient descent
power law
weight vector
artificial neural networks
least squares

back propagation
average case
loss function
learning curve
neural network
matrix factorization

random graphs
step size
random forests
complex networks
gaussian processes
vc dimension

collaborative filtering
learning algorithm
support vector machine
sample complexity
missing data
lower bound