Online distributed nonlinear regression via neural networks
dc.contributor.author | Ergen, Tolga | en_US |
dc.contributor.author | Kozat, Süleyman Serdar | en_US |
dc.coverage.spatial | Antalya, Turkey | en_US |
dc.date.accessioned | 2018-04-12T11:45:11Z | |
dc.date.available | 2018-04-12T11:45:11Z | |
dc.date.issued | 2017 | en_US |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.description | Date of Conference: 15-18 May 2017 | en_US |
dc.description | Conference Name: IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017 | en_US |
dc.description.abstract | In this paper, we study the nonlinear regression problem in a network of nodes and introduce long short term memory (LSTM) based algorithms. In order to learn the parameters of the LSTM architecture in an online manner, we put the LSTM equations into a nonlinear state space form and then introduce our distributed particle filtering (DPF) based training algorithm. Our training algorithm asymptotically achieves the optimal training performance. In our simulations, we illustrate the performance improvement achieved by the introduced algorithm with respect to the conventional methods. | en_US |
dc.description.provenance | Made available in DSpace on 2018-04-12T11:45:11Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 179475 bytes, checksum: ea0bedeb05ac9ccfb983c327e155f0c2 (MD5) Previous issue date: 2017 | en |
dc.identifier.doi | 10.1109/SIU.2017.7960220 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/37600 | |
dc.language.iso | Turkish | en_US |
dc.publisher | IEEE | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1109/SIU.2017.7960220 | en_US |
dc.source.title | Proceedings of the IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017 | en_US |
dc.subject | Distributed particle filtering | en_US |
dc.subject | Long short term memory network | en_US |
dc.subject | Nonlinear regression | en_US |
dc.subject | Online learning | en_US |
dc.subject | Monte Carlo methods | en_US |
dc.subject | Regression analysis | en_US |
dc.subject | Signal filtering and prediction | en_US |
dc.subject | State space methods | en_US |
dc.subject | Conventional methods | en_US |
dc.subject | Distributed particles | en_US |
dc.subject | Nonlinear regression problems | en_US |
dc.subject | Nonlinear state space | en_US |
dc.subject | Training algorithms | en_US |
dc.title | Online distributed nonlinear regression via neural networks | en_US |
dc.title.alternative | Sinir ağları ile çevrimiçi dağıtılmış doğrusal olmayan bağlanım | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Online distributed nonlinear regression via neural networks.pdf
- Size:
- 170.9 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full Printable Version