Low-variance Forward Gradients using Direct Feedback Alignment and momentum.

Florian Bacho Dominique F. Chu

Published in: Neural Networks (2024)

Keyphrases

low variance
real valued
learning rate
forward and backward
information retrieval
relevance feedback
user feedback
unbiased estimator
data sets
neural network
support vector machine
web search
convergence rate
image gradient
bi directional
probability values