Neural Networks Sequential Training Using Variational Gaussian Particle Filter

Beitrag bei einer Tagung
(Konferenzbeitrag)


Details zur Publikation

Autorinnen und Autoren: Halimeh MM, Brendel A, Kellermann W
Jahr der Veröffentlichung: 2019
Tagungsband: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Sprache: Englisch


Abstract

In this paper, we propose a sequential training algorithm for
feed-forward neural networks based on particle filtering. The proposed
algorithm uses variational learning to tailor a proposal density by
minimizing the variational energy. This density is then incorporated
into the Gaussian particle filter framework. The proposed algorithm and
an extension to it using evolutionary resampling are compared to
training a neural network using a random walk-based particle filter, an
extended Kalman filter, the use of variational learning only, and the
backpropagation algorithm, using a synthetic dataset generated by a
time-varying random process and a real dataset, where the proposed
approach resulted in a moderately lower training and testing errors and a
better convergence behavior, rendering the algorithm attractive for
uses such as neural networks pre-training.


FAU-Autorinnen und Autoren / FAU-Herausgeberinnen und Herausgeber

Brendel, Andreas
Professur für Nachrichtentechnik
Halimeh, MHD Modar
Lehrstuhl für Digitale Übertragung
Kellermann, Walter Prof. Dr.-Ing.
Professur für Nachrichtentechnik


Zitierweisen

APA:
Halimeh, M.M., Brendel, A., & Kellermann, W. (2019). Neural Networks Sequential Training Using Variational Gaussian Particle Filter. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brighton, GB.

MLA:
Halimeh, MHD Modar, Andreas Brendel, and Walter Kellermann. "Neural Networks Sequential Training Using Variational Gaussian Particle Filter." Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton 2019.

BibTeX: 

Zuletzt aktualisiert 2019-02-07 um 09:38