Hundreds of Mathematics books at half price + FREE shipping! Get yours now >>

Studies in Computational Intelligence

Supervised Sequence Labelling with Recurrent Neural Networks

Authors: Graves, Alex

  • Recent research in Supervised Sequence Labelling with Recurrent Neural Networks
  • New results in a hot topic
  • Written by leading experts
see more benefits

Buy this book

eBook $109.00
price for USA (gross)
valid through October 16, 2017
  • ISBN 978-3-642-24797-2
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $149.00
price for USA
valid through October 16, 2017
  • ISBN 978-3-642-24796-5
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $149.00
price for USA
  • ISBN 978-3-642-43218-7
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Rent the ebook  
  • Rental duration: 1 or 6 month
  • low-cost access
  • online reader with highlighting and note-making option
  • can be used across all devices
About this book

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.

Table of contents (9 chapters)

Buy this book

eBook $109.00
price for USA (gross)
valid through October 16, 2017
  • ISBN 978-3-642-24797-2
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $149.00
price for USA
valid through October 16, 2017
  • ISBN 978-3-642-24796-5
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $149.00
price for USA
  • ISBN 978-3-642-43218-7
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Rent the ebook  
  • Rental duration: 1 or 6 month
  • low-cost access
  • online reader with highlighting and note-making option
  • can be used across all devices
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Supervised Sequence Labelling with Recurrent Neural Networks
Authors
Series Title
Studies in Computational Intelligence
Series Volume
385
Copyright
2012
Publisher
Springer-Verlag Berlin Heidelberg
Copyright Holder
The Editor(s) (if applicable) and The Author(s) 2018
eBook ISBN
978-3-642-24797-2
DOI
10.1007/978-3-642-24797-2
Hardcover ISBN
978-3-642-24796-5
Softcover ISBN
978-3-642-43218-7
Series ISSN
1860-949X
Edition Number
1
Number of Pages
XIV, 146
Topics