Neural networks based online learning
Kozat, S. S.
2017 25th Signal Processing and Communications Applications Conference, SIU 2017
Institute of Electrical and Electronics Engineers Inc.
Item Usage Stats
MetadataShow full item record
In this paper, we investigate online nonlinear regression and introduce novel algorithms based on the long short term memory (LSTM) networks. We first put the underlying architecture in a nonlinear state space form and introduce highly efficient particle filtering (PF) based updates, as well as, extended Kalman filter (EKF) based updates. Our PF based training method guarantees convergence to the optimal parameter estimation under certain assumptions. We achieve this performance with a computational complexity in the order of the first order gradient based methods by controlling the number of particles. The experimental results illustrate significant performance improvements achieved by the introduced algorithms with respect to the conventional methods. © 2017 IEEE.
Long short term memory network
Extended Kalman filters
Monte Carlo methods
Signal filtering and prediction
State space methods
Nonlinear state space
Optimal parameter estimation
Short term memory
Published Version (Please cite this version)http://dx.doi.org/10.1109/SIU.2017.7960218
Showing items related by title, author, creator and subject.
Ozturk, C.; Huntington, A.; Aydinli, A.; Byun, Y.T.; Dagli, N. (IEEE, 2002)This paper reports a study on a compact filter fabricated using hybrid integration of compound semiconductors and polymers. A GaAs epilayer is glued onto a polymer channel waveguide forming a highly asymmetrical directional ...
Kurudere, S.; Erturk, V. B. (IEEE, 2013)A novel configuration for mechanically tunable combline bandpass filters is proposed, where the classical resonating rod-tuning screw combination is replaced with a simple printed circuit-tuning screw combination. Moreover, ...
Sayin, M.O.; Denizcan Vanli, N.; Kozat, S.S. (IEEE Computer Society, 2014)In this paper, we propose robust set-membership filtering algorithms against impulsive noise. Firstly, we introduce set-membership normalized least absolute difference algorithm (SM-NLAD). This algorithm provides robustness ...