Explainable artificial intelligence : (Record no. 5315)

MARC details
000 -LEADER
fixed length control field 02556naa a22003258i 4500
001 - CONTROL NUMBER
control field 00005315
003 - CONTROL NUMBER IDENTIFIER
control field FR-PaOEC
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20211006062616.0
006 - FIXED-LENGTH DATA ELEMENTS--ADDITIONAL MATERIAL CHARACTERISTICS
fixed length control field a o d i
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION
fixed length control field cr || |||m|n||
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 190601s2017 ||| o i|0| 0 eng d
035 ## - SYSTEM CONTROL NUMBER
System control number (FR-PaOEC)
040 ## - CATALOGING SOURCE
Original cataloging agency FR-PaOEC
Transcribing agency ES-MaONT
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Samek, Wojciech
9 (RLIN) 3410
245 10 - TITLE STATEMENT
Title Explainable artificial intelligence :
Remainder of title Understanding, visualizing and interpreting deep learning models /
Statement of responsibility, etc. Wojciech Samek, Thomas Wiegand and Klaus-Robert Müller
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Place of publication, distribution, etc. Geneva :
Name of publisher, distributor, etc. International Telecommunication Union,
Date of publication, distribution, etc. 2017.
300 ## - PHYSICAL DESCRIPTION
Extent 10 p.
336 ## - CONTENT TYPE
Content type term texto (visual)
Source isbdcontent
337 ## - MEDIA TYPE
Media type term electrónico
Source isbdmedia
338 ## - CARRIER TYPE
Carrier type term recurso en línea
Source rdacarrier
520 3# - SUMMARY, ETC.
Summary, etc. With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching, or even exceeding, the human level on an increasing number of complex tasks. Impressive examples of this development can be found in domains such as image classification, sentiment analysis, speech understanding or strategic game playing. However, because of their nested non-linear structure, these highly successful machine learning and artificial intelligence models are usually applied in a black-box manner, i.e. no information is provided about what exactly makes them arrive at their predictions. Since this lack of transparency can be a major drawback, e.g. in medical applications, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This paper summarizes recent developments in this field and makes a plea for more interpretability in artificial intelligence. Furthermore, it presents two approaches to explaining predictions of deep learning models, one method which computes the sensitivity of the prediction with respect to changes in the input and one approach which meaningfully decomposes the decision in terms of the input variables. These methods are evaluated on three classification tasks.
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Tecnologías habilitadoras digitales
9 (RLIN) 18
653 #4 - INDEX TERM--UNCONTROLLED
Uncontrolled term Science and Technology
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Wiegand, Thomas
9 (RLIN) 3413
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Müller, Klaus-Robert
9 (RLIN) 3330
773 0# - HOST ITEM ENTRY
Host Biblionumber 4843
Title ITU Journal: ICT Discoveries
Related parts Vol. 2018, no. 1, p. 39-48
Enumeration and first page 2018:1<39
International Standard Serial Number 2616-8375
856 40 - ELECTRONIC LOCATION AND ACCESS
Host name itu-ilibrary.org
Uniform Resource Identifier https://www.itu.int/dms_pub/itu-s/opb/journal/S-JOURNAL-ICTS.V1I1-2017-5-PDF-E.pdf
Link text Acceso al documento
Nonpublic note Abierto
Electronic format type pdf
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type Artículos
Source of classification or shelving scheme Universal Decimal Classification
Holdings
Withdrawn status Lost status Damaged status Not for loan Collection code Koha itemnumber Home library Current library Shelving location Date acquired Total Checkouts Barcode Date last seen Price effective from Koha item type Public note
      Acceso libre online Colección digital 6265 CDO CDO   12/09/2019   1000020175564 12/09/2019 12/09/2019 Artículos pdf
Copyright© ONTSI. Todos los derechos reservados.
x
Esta web está utilizando la política de Cookies de la entidad pública empresarial Red.es, M.P. se detalla en el siguiente enlace: aviso-cookies. Acepto