Zum Hauptinhalt springen Zur Suche springen Zur Hauptnavigation springen
Dekorationsartikel gehören nicht zum Leistungsumfang.
Supervised Sequence Labelling with Recurrent Neural Networks
Taschenbuch von Alex Graves
Sprache: Englisch

160,95 €*

-16 % UVP 192,59 €
inkl. MwSt.

Versandkostenfrei per Post / DHL

Lieferzeit 2-4 Werktage

Produkt Anzahl: Gib den gewünschten Wert ein oder benutze die Schaltflächen um die Anzahl zu erhöhen oder zu reduzieren.
Kategorien:
Beschreibung
Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools¿robust to input noise and distortion, able to exploit long-range contextual information¿that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary.

The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional recurrent neural networks extend the framework in a natural way to data with more than one spatio-temporal dimension, such as images and videos. Thirdly, the use of hierarchical subsampling makes it feasible to apply the framework to very large or high resolution sequences, such as raw audio or video.

Experimental validation is provided by state-of-the-art results in speech and handwriting recognition.
Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools¿robust to input noise and distortion, able to exploit long-range contextual information¿that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary.

The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional recurrent neural networks extend the framework in a natural way to data with more than one spatio-temporal dimension, such as images and videos. Thirdly, the use of hierarchical subsampling makes it feasible to apply the framework to very large or high resolution sequences, such as raw audio or video.

Experimental validation is provided by state-of-the-art results in speech and handwriting recognition.
Zusammenfassung

Recent research in Supervised Sequence Labelling with Recurrent Neural Networks

New results in a hot topic

Written by leading experts

Inhaltsverzeichnis
Introduction.- Supervised Sequence Labelling.- Neural Networks.- Long Short-Term Memory.- A Comparison of Network Architectures.- Hidden Markov Model Hybrids.- Connectionist Temporal Classification.- Multidimensional Networks.- Hierarchical Subsampling Networks.
Details
Erscheinungsjahr: 2014
Fachbereich: Technik allgemein
Genre: Mathematik, Medizin, Naturwissenschaften, Technik
Rubrik: Naturwissenschaften & Technik
Medium: Taschenbuch
Inhalt: xiv
146 S.
ISBN-13: 9783642432187
ISBN-10: 3642432182
Sprache: Englisch
Einband: Kartoniert / Broschiert
Autor: Graves, Alex
Hersteller: Springer-Verlag GmbH
Springer Berlin Heidelberg
Verantwortliche Person für die EU: Springer Verlag GmbH, Tiergartenstr. 17, D-69121 Heidelberg, juergen.hartmann@springer.com
Maße: 235 x 155 x 9 mm
Von/Mit: Alex Graves
Erscheinungsdatum: 13.04.2014
Gewicht: 0,254 kg
Artikel-ID: 105335603
Zusammenfassung

Recent research in Supervised Sequence Labelling with Recurrent Neural Networks

New results in a hot topic

Written by leading experts

Inhaltsverzeichnis
Introduction.- Supervised Sequence Labelling.- Neural Networks.- Long Short-Term Memory.- A Comparison of Network Architectures.- Hidden Markov Model Hybrids.- Connectionist Temporal Classification.- Multidimensional Networks.- Hierarchical Subsampling Networks.
Details
Erscheinungsjahr: 2014
Fachbereich: Technik allgemein
Genre: Mathematik, Medizin, Naturwissenschaften, Technik
Rubrik: Naturwissenschaften & Technik
Medium: Taschenbuch
Inhalt: xiv
146 S.
ISBN-13: 9783642432187
ISBN-10: 3642432182
Sprache: Englisch
Einband: Kartoniert / Broschiert
Autor: Graves, Alex
Hersteller: Springer-Verlag GmbH
Springer Berlin Heidelberg
Verantwortliche Person für die EU: Springer Verlag GmbH, Tiergartenstr. 17, D-69121 Heidelberg, juergen.hartmann@springer.com
Maße: 235 x 155 x 9 mm
Von/Mit: Alex Graves
Erscheinungsdatum: 13.04.2014
Gewicht: 0,254 kg
Artikel-ID: 105335603
Sicherheitshinweis

Ähnliche Produkte

Ähnliche Produkte