Dynamical variational autoencoders : (Record no. 172349)

MARC details
000 -LEADER
fixed length control field 02081nam a22002657a 4500
003 - CONTROL NUMBER IDENTIFIER
control field IIITD
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20240506131932.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 240406b xxu||||| |||| 00| 0 eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9781680839128
040 ## - CATALOGING SOURCE
Original cataloging agency IIITD
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 006.1
Item number GIR-D
245 ## - TITLE STATEMENT
Title Dynamical variational autoencoders :
Remainder of title a comprehensive review
Statement of responsibility, etc by Laurent Girin ... [et al.]
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Place of publication, distribution, etc Boston :
Name of publisher, distributor, etc Now Publishers,
Date of publication, distribution, etc ©2021
300 ## - PHYSICAL DESCRIPTION
Extent 187 p. ;
Dimensions 23 cm.
500 ## - GENERAL NOTE
General note Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data vectors are processed independently. Recently, a series of papers have presented different extensions of the VAE to process sequential data, which model not only the latent space but also the temporal dependencies within a sequence of data vectors and corresponding latent vectors, relying on recurrent neural networks or state-space models. In this monograph, we perform a literature review of these models. We introduce and discuss a general class of models, called dynamical variational autoencoders (DVAEs), which encompasses a large subset of these temporal VAE extensions. Then, we present in detail seven recently proposed DVAE models, with an aim to homogenize the notations and presentation lines, as well as to relate these models with existing classical temporal models. We have reimplemented those seven DVAE models and present the results of an experimental benchmark conducted on the speech analysis-resynthesis task (the PyTorch code is made publicly available). The monograph concludes with a discussion on important issues concerning the DVAE class of models and future research guidelines.
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element Dynamical
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element Variational Autoencoders
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Girin, Laurent
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Leglaive, Simon
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Bie, Xiaoyu
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Diard, Julien
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Hueber, Thomas
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Alameda-Pineda, Xavier
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type Books
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Collection code Home library Current library Shelving location Date acquired Bill No. Bill Date Cost, normal purchase price PO No. PO Date Total Checkouts Full call number Barcode Date last seen Cost, replacement price Price effective from Vendor/Supplier Koha item type Public note
    Dewey Decimal Classification   Loan on demand Computer Science and Engineering IIITD IIITD Reference 06/04/2024 1170934 2024-03-28 5582 Email2-05-03-2024 2024-03-05   CB 006.1 GIR-D 012796 05/05/2024 $99 06/04/2024 Atlantic Publishers & Distributors (P) Ltd. Books DBT Project Grant
© 2024 IIIT-Delhi, library@iiitd.ac.in