Mercurial > ift6266

comparison writeup/mlj_submission.tex @ 588:9a6abcf143e8

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
merge
author fsavard
date Thu, 30 Sep 2010 17:51:46 -0400
parents b1be957dd1be f5a198b2854a
children 1538412ee69d 4672fb6b4385
comparison
equal deleted inserted replaced
587:b1be957dd1be 588:9a6abcf143e8
127 It is also only recently that successful algorithms were proposed to 127 It is also only recently that successful algorithms were proposed to
128 overcome some of these difficulties. All are based on unsupervised 128 overcome some of these difficulties. All are based on unsupervised
129 learning, often in an greedy layer-wise ``unsupervised pre-training'' 129 learning, often in an greedy layer-wise ``unsupervised pre-training''
130 stage~\citep{Bengio-2009}. One of these layer initialization techniques, 130 stage~\citep{Bengio-2009}. One of these layer initialization techniques,
131 applied here, is the Denoising 131 applied here, is the Denoising
132 Auto-encoder~(DA)~\citep{VincentPLarochelleH2008-very-small} (see Figure~\ref{fig:da}), 132 Auto-encoder~(DA)~\citep{VincentPLarochelleH2008} (see Figure~\ref{fig:da}),
133 which 133 which
134 performed similarly or better than previously proposed Restricted Boltzmann 134 performed similarly or better than previously proposed Restricted Boltzmann
135 Machines in terms of unsupervised extraction of a hierarchy of features 135 Machines in terms of unsupervised extraction of a hierarchy of features
136 useful for classification. Each layer is trained to denoise its 136 useful for classification. Each layer is trained to denoise its
137 input, creating a layer of features that can be used as input for the next layer. 137 input, creating a layer of features that can be used as input for the next layer.