[Adapt] Abstract of the presentation at the seminar of tomorrow

[姜凯]

Hi adapters,

At the seminar of tomorrow, I will give a talk about representation
learning to you. I write a abstract of it here. Hope you enjoy it~

*abstract*

This talk is about representation learning, or in other words, feature
learning. The success of machine learning algorithms generally depends on
data representation, and we hypothesize that this is because different
representations can entangle and hide more or less the different
explanatory factors of variation behind the data. Representation learning
of the data makes it easier to extract useful information when building
classifiers or other predictors. In this presentation, I will introduce
some useful representation learning, such as auto-encoder, sparse
auto-encoder, restricted Boltzmann Machine, as well as corresponding deep
learning methods, for example deep auto-encoder, deep brief network.

cheers,
Jacky

-- 
Jacky Jiang* *(*姜凯*)
Graduate
Shanghai Jiao Tong University
Department of Computer Science and Engineering
No.800 Dongchuan Road,Shanghai,P.R.China
Tel:15000677334
Email:jkai421 at gmail.com
<http://Email:jkai421@gmail.com/jkai@sjtu.edu.cn>(urgent
and significant)
jkai at sjtu.edu.cn <http://Email:jkai421@gmail.com/jkai@sjtu.edu.cn>(normal)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20130402/80d8412e/attachment.html>