Low complexity efficient online learning algorithms using LSTM networks
| buir.advisor | Kozat, Süleyman Serdar | |
| dc.contributor.author | Mirza, Ali Hassan | |
| dc.date.accessioned | 2018-12-13T13:14:54Z | |
| dc.date.available | 2018-12-13T13:14:54Z | |
| dc.date.copyright | 2018-12 | |
| dc.date.issued | 2018-12 | |
| dc.date.submitted | 2018-12-12 | |
| dc.department | Department of Electrical and Electronics Engineering | en_US |
| dc.description | Cataloged from PDF version of article. | en_US |
| dc.description | Thesis (M.S.): Bilkent University, Department of Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University, 2018. | en_US |
| dc.description | Includes bibliographical references (leaves 84-88). | en_US |
| dc.description.abstract | In this thesis, we implement efficient online learning algorithms using the Long Short Term Memory (LSTM) networks with low time and computational complexity. In Chapter 2, we investigate efficient covariance information-based online learning using the LSTM networks known as Co-LSTM networks. We utilize the covariance information into the LSTM gating structure and propose various effi- cient models. We reduce the computational complexity by applying the Weight Matrix Factorization (WMF) trick and derive the additive gradient based updates. In Chapter 3, we give a practical application of the network intrusion detection using the Co-LSTM networks. In Chapter 4, we propose a boosted binary version of Tree-LSTM networks which we call BBT-LSTM networks. We introduce the depth and windowing factor into the N-ary Tree-LSTM networks where each LSTM node is binarily split and the whole tree architecture grows in a balanced manner. In order to reduce the computational complexity of the BBT-LSTM networks, we apply WMF trick, replace the regular multiplication operator with the energy efficient operator and finally introduce the slicing operation on the BBT-LSTM network weight matrices. In Chapter 5, we propose another low complexity LSTM network based on a minimum number of hopping over the input data sequence. We study two methods to select the appropriate value of the hopping distance. Through an extensive set of experiments using the real-life data sets, we demonstrate the significant increase in the performance of the proposed algorithms at the end of each chapter. | en_US |
| dc.description.degree | M.S. | en_US |
| dc.description.provenance | Submitted by Betül Özen (ozen@bilkent.edu.tr) on 2018-12-13T13:14:54Z No. of bitstreams: 1 thesis .pdf: 2009201 bytes, checksum: 7477e2a043d1263c420fb9ce6f2a8eae (MD5) | en |
| dc.description.provenance | Made available in DSpace on 2018-12-13T13:14:54Z (GMT). No. of bitstreams: 1 thesis .pdf: 2009201 bytes, checksum: 7477e2a043d1263c420fb9ce6f2a8eae (MD5) Previous issue date: 2018-12 | en |
| dc.description.statementofresponsibility | by Ali Hassan Mirza. | en_US |
| dc.embargo.release | 2020-12-10 | |
| dc.format.extent | xvi, 97 leaves : charts (some color) ; 30 cm. | en_US |
| dc.identifier.itemid | B159503 | |
| dc.identifier.uri | http://hdl.handle.net/11693/48199 | |
| dc.language.iso | English | en_US |
| dc.publisher | Bilkent University | en_US |
| dc.rights | info:eu-repo/semantics/openAccess | en_US |
| dc.subject | Online Learning | en_US |
| dc.subject | LSTM | en_US |
| dc.subject | Covariance | en_US |
| dc.subject | Tree-LSTM | en_US |
| dc.subject | Boosting | en_US |
| dc.subject | Regression | en_US |
| dc.subject | WMF | en_US |
| dc.title | Low complexity efficient online learning algorithms using LSTM networks | en_US |
| dc.title.alternative | UKSB ağları ile düşük karmaşıklığa sahip verimli çevrimiçi öğrenme algoritmaları | en_US |
| dc.type | Thesis | en_US |