An approach for output decoding of neural networks

Tobias Strauß; Roger Labahn; Gundram Leifert; Welf Wustlich

doi:10.18453/rosdok_id00005820

zum übergeordneten Dokument

Tobias Strauß Roger Labahn Gundram Leifert Welf Wustlich

An approach for output decoding of neural networks

University of Rostock, Institute of Mathematics, 2012

https://doi.org/10.18453/rosdok_id00005820

Abstract: 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.

Workingpaper Freier Zugang

Titel:

An approach for output decoding of neural networks

Schriftenreihe:

Preprints aus dem Institut für Mathematik, 12/3

Beteiligte Personen:

Tobias Strauß[VerfasserIn]
	0000-0002-5344-4188
	1136294554
Roger Labahn[VerfasserIn]
	0000-0003-1901-9644
	170999645
Gundram Leifert[VerfasserIn]
Welf Wustlich[VerfasserIn]

Zusammenfassung:

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. [Englisch]

Dokumenttyp:

Workingpaper

Einrichtung:

Mathematisch-Naturwissenschaftliche Fakultät

Sprache:

Englisch

Sachgruppe der DNB:

510 Mathematik

Umfang:

1 Online-Ressource (7 Seiten)

Veröffentlichung /
Entstehung:

Rostock: University of Rostock, Institute of Mathematics