eBooks :: Kembali

eBooks :: Kembali

Supervised sequence labelling with recurrent neural networks

Alex Graves ([, Springer], 2012)

 Abstrak

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.

 File Digital: 1

Shelf
 Supervised Sequence Labelling with Recurrent Neural Networks.pdf :: Unduh

LOGIN required

 Metadata

Jenis Koleksi : eBooks
No. Panggil : e20398893
Entri utama-Nama orang :
Subjek :
Penerbitan : Berlin: [, Springer], 2012
Sumber Pengatalogan: LibUI eng rda
Tipe Konten: text
Tipe Media: computer
Tipe Pembawa: online resource
Deskripsi Fisik: xii, 141 pages : illustration
Tautan: http://link.springer.com/book/10.1007%2F978-3-642-24797-2
Lembaga Pemilik:
Lokasi:
  • Ketersediaan
  • Ulasan
  • Sampul
No. Panggil No. Barkod Ketersediaan
e20398893 TERSEDIA
Ulasan:
Tidak ada ulasan pada koleksi ini: 20398893
Cover