From da8251bfa40a73d14a7f721d2e43109f0c230edd Mon Sep 17 00:00:00 2001
From: yaolubrain <yaolubrain@gmail.com>
Date: Wed, 7 Oct 2015 15:11:53 +0300
Subject: [PATCH] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 5115a60..ab153a1 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@ This repo contains the experiment code in paper
 
 [Unsupervised Learning on Neural Network Outputs](http://arxiv.org/abs/1506.00990)
 
-The paper presents a new zero-shot learning method, which achieves the state-of-the-art results in ImageNet fall2011.
+The paper presents a new zero-shot learning method, which achieves the state-of-the-art results on ImageNet fall2011.
 
 The CNN model is GoogeLeNet with [Caffe] (http://caffe.berkeleyvision.org/) implementation. The image format convertor (image2hdf5) is from [Toronto Deep Learning](https://github.com/TorontoDeepLearning/convnet).