% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Yegenoglu:889208,
author = {Yegenoglu, Alper and Krajsek, Kai and Diaz, Sandra and
Herty, Michael},
title = {{E}nsemble {K}alman {F}ilter {O}ptimizing {D}eep {N}eural
{N}etworks: {A}n {A}lternative {A}pproach to
{N}on-performing {G}radient {D}escent; 5th ed.},
volume = {12566},
address = {Cham},
publisher = {Springer},
reportid = {FZJ-2021-00117},
series = {Lecture Notes in Computer Science},
pages = {78-92},
year = {2020},
comment = {Machine Learning, Optimization, and Data Science},
booktitle = {Machine Learning, Optimization, and
Data Science},
abstract = {The successful training of deep neural networks is
dependent on initialization schemes and choice of activation
functions. Non-optimally chosen parameter settings lead to
the known problem of exploding or vanishing gradients. This
issue occurs when gradient descent and backpropagation are
applied. For this setting the Ensemble Kalman Filter (EnKF)
can be used as an alternative optimizer when training neural
networks. The EnKF does not require the explicit calculation
of gradients or adjoints and we show this resolves the
exploding and vanishing gradient problem. We analyze
different parameter initializations, propose a dynamic
change in ensembles and compare results to established
methods.},
month = {Jul},
date = {2020-07-19},
organization = {The Sixth International Conference on
Machine Learning, Optimization, and
Data Science, Siena (Italy), 19 Jul
2020 - 22 Jul 2020},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {511 - Computational Science and Mathematical Methods
(POF3-511) / SMHB - Supercomputing and Modelling for the
Human Brain (HGF-SMHB-2013-2017) / CSD-SSD - Center for
Simulation and Data Science (CSD) - School for Simulation
and Data Science (SSD) (CSD-SSD-20190612) / SLNS - SimLab
Neuroscience (Helmholtz-SLNS) / HDS LEE - Helmholtz School
for Data Science in Life, Earth and Energy (HDS LEE)
(HDS-LEE-20190612) / PhD no Grant - Doktorand ohne besondere
Förderung (PHD-NO-GRANT-20170405) / HAF - Helmholtz
Analytics Framework (ZT-I-0003)},
pid = {G:(DE-HGF)POF3-511 / G:(DE-Juel1)HGF-SMHB-2013-2017 /
G:(DE-Juel1)CSD-SSD-20190612 / G:(DE-Juel1)Helmholtz-SLNS /
G:(DE-Juel1)HDS-LEE-20190612 /
G:(DE-Juel1)PHD-NO-GRANT-20170405 / G:(DE-HGF)ZT-I-0003},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
doi = {10.1007/978-3-030-64580-9_7},
url = {https://juser.fz-juelich.de/record/889208},
}