000 02556naa a22003258i 4500
999 _c5315
_d5315
001 00005315
003 FR-PaOEC
005 20211006062616.0
006 a o d i
007 cr || |||m|n||
008 190601s2017 ||| o i|0| 0 eng d
035 _a(FR-PaOEC)
040 _aFR-PaOEC
_cES-MaONT
100 _aSamek, Wojciech
_93410
245 1 0 _aExplainable artificial intelligence :
_bUnderstanding, visualizing and interpreting deep learning models /
_cWojciech Samek, Thomas Wiegand and Klaus-Robert Müller
260 _aGeneva :
_bInternational Telecommunication Union,
_c2017.
300 _a10 p.
336 _atexto (visual)
_2isbdcontent
337 _aelectrónico
_2isbdmedia
338 _arecurso en línea
_2rdacarrier
520 3 _aWith 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 _aTecnologías habilitadoras digitales
_918
653 4 _aScience and Technology
700 _aWiegand, Thomas
_93413
700 1 _aMüller, Klaus-Robert
_93330
773 0 _04843
_tITU Journal: ICT Discoveries
_gVol. 2018, no. 1, p. 39-48
_q2018:1<39
_x2616-8375
856 4 0 _aitu-ilibrary.org
_uhttps://www.itu.int/dms_pub/itu-s/opb/journal/S-JOURNAL-ICTS.V1I1-2017-5-PDF-E.pdf
_yAcceso al documento
_x0
_qpdf
942 _cART
_2udc