Tools | Bookmark & Share | Make MrWhy My Homepage
MrWhy.com
Go
MrWhy.com » Videos » Extracting and Composing Robust Features with Denoising Autoencoders
Extracting and Composing Robust Features with Denoising Autoencoders
Extracting and Composing Robust Features with Denoising Autoencoders
Report
Extracting and Composing Robust Features with Denoising Autoencoders
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful itermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.
Channel: VideoLectures
Category: Educational
Video Length: 0
Date Found: October 12, 2010
Date Produced: August 29, 2008
View Count: 0
 
MrWhy.com Special Offers
1
2
3
4
5
 
About Us: About MrWhy.com | Advertise on MrWhy.com | Contact MrWhy.com | Privacy Policy | MrWhy.com Partners
Answers: Questions and Answers | Browse by Category
Comparison Shopping: Comparison Shopping | Browse by Category | Top Searches
Shop eBay: Shop eBay | Browse by Category
Shop Amazon: Shop Amazon | Browse by Category
Videos: Video Search | Browse by Category
Web Search: Web Search | Browse by Searches
Copyright © 2011 MrWhy.com. All rights reserved.