Higher Order Recurrent Neural Network for Language Modeling

Simple item page
dc.contributor.advisorJiang, Hui
dc.creatorBidgoli, Rohollah Soltani
dc.date.accessioned2016-09-20T18:56:37Z
dc.date.available2016-09-20T18:56:37Z
dc.date.copyright2016-04-28
dc.date.issued2016-09-20
dc.date.updated2016-09-20T18:56:37Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractIn this thesis, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all recurrently fed to the hidden layers as feedback through different weighted paths. By extending the popular recurrent structure in RNNs, we provide the models with better short-term memory mechanism to learn long term dependency in sequences. Analogous to digital filters in signal processing, we call these structures as higher order RNNs (HORNNs). Similar to RNNs, HORNNs can also be learned using the back-propagation through time method. HORNNs are generally applicable to a variety of sequence modelling tasks. In this work, we have examined HORNNs for the language modeling task using two popular data sets, namely the Penn Treebank (PTB) and English text8 data sets. Experimental results have shown that the proposed HORNNs yield the state-of-the-art performance on both data sets, significantly outperforming the regular RNNs as well as the popular LSTMs.
dc.identifier.urihttp://hdl.handle.net/10315/32337
dc.language.isoen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywordsMachine Learning
dc.subject.keywordsDeep Learning
dc.subject.keywordsNeural Network
dc.subject.keywordsRecurrent Neural Network
dc.subject.keywordsLanguage Modeling
dc.subject.keywordsHigher Order Recurrent Neural Network
dc.titleHigher Order Recurrent Neural Network for Language Modeling
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SoltaniBidgoli_Rohollah_2016_Masters.pdf
Size:
487.06 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.83 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.38 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science and Engineering

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.