TY - CHAP

T1 - Comparison of Backpropagation and Kalman Filter-based Training for Neural Networks

AU - Luttmann, Laurin

AU - Mercorelli, Paolo

N1 - Conference code: 25

PY - 2021/10/20

Y1 - 2021/10/20

N2 - This work describes and compares the backpropagation algorithm with the extended Kalman filter (EKF), a second-order training method which can be applied to the problem of learning neural network parameters and is known to converge in only a few iterations. The algorithms are compared with respect to their effectiveness and speed of convergence using simulated data for both, a regression and a classification task.

AB - This work describes and compares the backpropagation algorithm with the extended Kalman filter (EKF), a second-order training method which can be applied to the problem of learning neural network parameters and is known to converge in only a few iterations. The algorithms are compared with respect to their effectiveness and speed of convergence using simulated data for both, a regression and a classification task.

KW - Backpropagation Algorithm

KW - Kalman Filter

KW - Neural Networks

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85123317452&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/b493928c-948e-347f-8765-b1efa3182495/

U2 - 10.1109/ICSTCC52150.2021.9607274

DO - 10.1109/ICSTCC52150.2021.9607274

M3 - Article in conference proceedings

AN - SCOPUS:85123317452

SN - 978-1-6654-3055-5

T3 - International Conference on System Theory, Control and Computing

SP - 234

EP - 241

BT - 2021 25th International Conference on System Theory, Control and Computing (ICSTCC)

A2 - Ferariu, Lavinia

A2 - Matcovschi, Mihaela-Hanako

A2 - Ungureanu, Florina

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

T2 - 25th International Conference on System Theory, Control and Computing

Y2 - 20 October 2021 through 23 October 2021

ER -