TY  - BOOK
AU  - Strauß, Tobias
AU  - Labahn, Roger
AU  - Leifert, Gundram
AU  - Wustlich, Welf
PY  - 2012
DA  - 2012//
TI  - An  approach for output decoding of neural networks
T3  - Preprints aus dem Institut für Mathematik
CY  - Germany; Rostock
AB  - We review two decoding methods for recurrent neural networks – based on the well known weighted Levenshtein distance and the connectionist temporal classification (CTC) – and we introduce a new method – the dynamic Levenstein distance (DynWL). We compare these three methods analytically in terms of time complexity and error performance. Although the approaches are different, there are deep connections between These ways of decoding. Finally, we test on the Arabic and French ICDAR data sets. Our experiments show that CTC yields the smallest error rates. Nevertheless, there are scenarios where DynWL is a good choice between performance and time complexity.<eng>
UR  - https://purl.uni-rostock.de/rosdok/id00005820
UR  - https://doi.org/10.18453/rosdok_id00005820
DO  - 10.18453/rosdok_id00005820
LA  - English
N1  - Tobias Strauß, Roger Labahn, Gundram Leifert, Welf Wustlich
ID  - 1986180786
ER  -