From 3eb226834d822191027b914c366757fa81c8fcbe Mon Sep 17 00:00:00 2001 From: GaetanMarceauCaron Date: Fri, 15 Apr 2016 16:27:55 +0200 Subject: small modif --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index 9c6e86d..1dfa31d 100644 --- a/README.md +++ b/README.md @@ -235,8 +235,7 @@ As always, the step-size must be chosen accordingly. Two additional arguments are also possible: * gamma (default=0.01): determine the update rate of the metric for a minibatch setting, i.e., (1-gamma) * oldMetric + gamma newMetric. Smaller minibatches require a smaller gamma. A default value depending on the size of the minibatches is `gamma = 1. - torch.pow(1.-1./nTraining,miniBatchSize)` where `nTraining` is the number of training examples of the dataset and `miniBatchSize` is the number of training examples per minibatch. * qdFlag (default=true): Whether to use the quasi-diagonal reduction (true) or only the diagonal (false). The former should be better. - -Replacing Linear by QDRiemmaNNLinear is a straightforward implementation of the outer product gradient descent. +This module is a straightforward implementation of the outer product gradient descent. ## Requirements -- cgit v1.2.3