Supervised Sequence Labelling with Recurrent Neural Networks: Studies in Computational Intelligence, cartea 385
Autor Alex Gravesen Limba Engleză Paperback – 13 apr 2014
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.
Toate formatele și edițiile | Preț | Express |
---|---|---|
Paperback (1) | 1128.29 lei 6-8 săpt. | |
Springer Berlin, Heidelberg – 13 apr 2014 | 1128.29 lei 6-8 săpt. | |
Hardback (1) | 1132.17 lei 6-8 săpt. | |
Springer Berlin, Heidelberg – 9 feb 2012 | 1132.17 lei 6-8 săpt. |
Din seria Studies in Computational Intelligence
- 50% Preț: 264.48 lei
- 70% Preț: 235.75 lei
- 20% Preț: 1134.78 lei
- 20% Preț: 966.66 lei
- 20% Preț: 1423.29 lei
- 20% Preț: 168.78 lei
- 18% Preț: 1089.74 lei
- 20% Preț: 565.38 lei
- 20% Preț: 636.14 lei
- 20% Preț: 1026.49 lei
- 20% Preț: 1546.90 lei
- 20% Preț: 630.47 lei
- 20% Preț: 644.20 lei
- 20% Preț: 973.14 lei
- 20% Preț: 970.73 lei
- 20% Preț: 969.90 lei
- 20% Preț: 1142.04 lei
- 20% Preț: 1415.20 lei
- 20% Preț: 1020.82 lei
- 20% Preț: 1026.49 lei
- 20% Preț: 1024.85 lei
- 18% Preț: 2449.69 lei
- 20% Preț: 969.09 lei
- 20% Preț: 1142.04 lei
- 20% Preț: 1140.44 lei
- 20% Preț: 1021.64 lei
- 20% Preț: 1430.55 lei
- 18% Preț: 1375.05 lei
- 18% Preț: 1102.11 lei
- 20% Preț: 1018.40 lei
- 20% Preț: 987.68 lei
- 20% Preț: 1024.07 lei
- 20% Preț: 1249.53 lei
- 20% Preț: 1019.22 lei
- 20% Preț: 968.30 lei
- 20% Preț: 1146.08 lei
- 20% Preț: 1138.80 lei
- 20% Preț: 1037.78 lei
- 20% Preț: 1140.44 lei
- 20% Preț: 1142.87 lei
- 20% Preț: 1429.76 lei
- 18% Preț: 985.35 lei
- 20% Preț: 977.17 lei
- 20% Preț: 1034.54 lei
- 20% Preț: 1262.78 lei
- 20% Preț: 974.89 lei
- 20% Preț: 1027.45 lei
- 20% Preț: 924.65 lei
- 20% Preț: 1149.31 lei
- 20% Preț: 1428.13 lei
Preț: 1128.29 lei
Preț vechi: 1410.36 lei
-20% Nou
Puncte Express: 1692
Preț estimativ în valută:
216.00€ • 224.52$ • 179.09£
216.00€ • 224.52$ • 179.09£
Carte tipărită la comandă
Livrare economică 05-19 februarie 25
Preluare comenzi: 021 569.72.76
Specificații
ISBN-13: 9783642432187
ISBN-10: 3642432182
Pagini: 160
Ilustrații: XIV, 146 p.
Dimensiuni: 155 x 235 x 8 mm
Greutate: 0.25 kg
Ediția:2012
Editura: Springer Berlin, Heidelberg
Colecția Springer
Seria Studies in Computational Intelligence
Locul publicării:Berlin, Heidelberg, Germany
ISBN-10: 3642432182
Pagini: 160
Ilustrații: XIV, 146 p.
Dimensiuni: 155 x 235 x 8 mm
Greutate: 0.25 kg
Ediția:2012
Editura: Springer Berlin, Heidelberg
Colecția Springer
Seria Studies in Computational Intelligence
Locul publicării:Berlin, Heidelberg, Germany
Public țintă
ResearchCuprins
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.
Textul de pe ultima copertă
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.
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.
Caracteristici
Recent research in Supervised Sequence Labelling with Recurrent Neural Networks New results in a hot topic Written by leading experts