A
new approach for cells in multidimensional recurrent neural networks
Leifert, Gundram
VerfasserIn
aut
Strauß, Tobias
1984-
VerfasserIn
aut
Labahn, Roger
1959-
VerfasserIn
aut
Wustlich, Welf
VerfasserIn
aut
text
Text
gw
2012
monographic
XA-DE
Rostock
University of Rostock, Institute of Mathematics
publisher
2012
Rostock
Universitätsbibliothek
distributor
eng
1 Online-Ressource (22 Seiten)
A recent approach for offline handwriting recognition is to use multidimensional recurrent neural networks (MDRNN) with connectionist temporal classification which has shown to yield very good results on several datasets. MDRNNs contain special units – multidimensional Long Short-Term Memory (MDLSTM) cells. These cells suffer from instability especially for higher dimensionality. We analyze the reasons for this effect and introduce several cells with better stability. We present a method to design stable multidimensional cells using the theory of linear shift invariant systems. The new cells are compared to MDLSTMs on the Arabic and French ICDAR datasets, where they yield better results.<eng>
Open Access
Urheberrechtsschutz 1.0
Gundram Leifert, Tobias Strauß, Roger Labahn, Welf Wustlich
510
https://purl.uni-rostock.de/rosdok/id00005819
Preprints aus dem Institut für Mathematik
12/4
urn:nbn:de:gbv:28-rosdok_id00005819-6
10.18453/rosdok_id00005819
1621162786
rda
DE-627
261010
1986180778
20261013T150720.0
Converted from MARCXML to MODS version 3.8 using MARC21slim2MODS3-8_XSLT1-0.xsl
(Revision 1.174 20250328)
ger