aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/python/training/rmsprop.py
diff options
context:
space:
mode:
Diffstat (limited to 'tensorflow/python/training/rmsprop.py')
-rw-r--r--tensorflow/python/training/rmsprop.py2
1 files changed, 2 insertions, 0 deletions
diff --git a/tensorflow/python/training/rmsprop.py b/tensorflow/python/training/rmsprop.py
index d046456c85..ebec725b7b 100644
--- a/tensorflow/python/training/rmsprop.py
+++ b/tensorflow/python/training/rmsprop.py
@@ -26,6 +26,8 @@ mean_square = decay * mean_square{t-1} + (1-decay) * gradient ** 2
mom = momentum * mom{t-1} + learning_rate * g_t / sqrt(mean_square + epsilon)
delta = - mom
+This implementation of RMSProp uses plain momentum, not Nesterov momentum.
+
The centered version additionally maintains a moving (discounted) average of the
gradients, and uses that average to estimate the variance: