From 5952a8146bb45334b05f401a44a0b8cac7b39982 Mon Sep 17 00:00:00 2001 From: Jingyuan Liu Date: Sun, 18 Mar 2018 21:17:56 +0800 Subject: [PATCH] Update README.md --- CNN-sentence_classification/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CNN-sentence_classification/README.md b/CNN-sentence_classification/README.md index c0d33942..ee752779 100644 --- a/CNN-sentence_classification/README.md +++ b/CNN-sentence_classification/README.md @@ -55,7 +55,7 @@ According to the paper and experiment, I set: |20|\(h,300,100\)|0.5|0.0001|50| h = [3,4,5] -If the accuracy is not improved, the learning rate will /*0.8. +If the accuracy is not improved, the learning rate will \*0.8. ## Result I just tried one dataset : MR. (Other 6 dataset in paper SST-1, SST-2, TREC, CR, MPQA)