Online distributed nonlinear regression via neural networks
Author
Ergen, Tolga
Kozat, Süleyman Serdar
Date
2017Source Title
Proceedings of the IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017
Publisher
IEEE
Language
Turkish
Type
Conference PaperItem Usage Stats
143
views
views
105
downloads
downloads
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.
Keywords
Distributed particle filteringLong short term memory network
Nonlinear regression
Online learning
Monte Carlo methods
Regression analysis
Signal filtering and prediction
State space methods
Conventional methods
Distributed particles
Nonlinear regression problems
Nonlinear state space
Training algorithms