From 6e07ceb0a88bcc8fdca6668c0cfe3a873fbcee45 Mon Sep 17 00:00:00 2001
From: tengerye <yetengqi@gmail.com>
Date: Tue, 26 Jan 2016 16:26:19 +0000
Subject: [PATCH] README.md

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 7f6b9ee..4c399cb 100644
--- a/README.md
+++ b/README.md
@@ -7,10 +7,10 @@ yetengqi@gmail.com
 
 ------------------------------------------------------------------------
 
-// orthogonal-denoising-autoencoder
+<!-- orthogonal-denoising-autoencoder -->
 This Python code implements the Orthogonal Denoising Autoencoders, which explianed in the paper "Learning Multiple Views with Orthogonal Denoising Autoencoders", best paper, Multimedia Modeling, 2016.
 
-// Multi-view learning techniques are necessary when data is described by multiple distinct feature sets because single-view learning algorithms tend to overfit on these high-dimensional data. Prior successful approaches followed either consensus or complementary principles. Recent work has focused on learning both the shared and private latent spaces of views in order to take advantage of both principles. However, these methods can not ensure that the latent spaces are strictly independent through encouraging the orthogonality in their objective functions. Also little work has explored representation learning techniques for multi-view learning. In this paper, we use the denoising autoencoder to learn shared and private latent spaces, with orthogonal constraints -- disconnecting every private latent space from the remaining views. Instead of computationally expensive optimization, we adapt the backpropagation algorithm to train our model.
+<!-- Multi-view learning techniques are necessary when data is described by multiple distinct feature sets because single-view learning algorithms tend to overfit on these high-dimensional data. Prior successful approaches followed either consensus or complementary principles. Recent work has focused on learning both the shared and private latent spaces of views in order to take advantage of both principles. However, these methods can not ensure that the latent spaces are strictly independent through encouraging the orthogonality in their objective functions. Also little work has explored representation learning techniques for multi-view learning. In this paper, we use the denoising autoencoder to learn shared and private latent spaces, with orthogonal constraints -- disconnecting every private latent space from the remaining views. Instead of computationally expensive optimization, we adapt the backpropagation algorithm to train our model. -->
 
 
 Files provided: