000 04394nam a22005535i 4500
001 978-3-030-75178-4
003 DE-He213
005 20240423125447.0
007 cr nn 008mamaa
008 210626s2021 sz | s |||| 0|eng d
020 _a9783030751784
_9978-3-030-75178-4
024 7 _a10.1007/978-3-030-75178-4
_2doi
050 4 _aQ325.5-.7
072 7 _aUYQM
_2bicssc
072 7 _aMAT029000
_2bisacsh
072 7 _aUYQM
_2thema
082 0 4 _a006.31
_223
100 1 _aNikolenko, Sergey I.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
245 1 0 _aSynthetic Data for Deep Learning
_h[electronic resource] /
_cby Sergey I. Nikolenko.
250 _a1st ed. 2021.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2021.
300 _aXII, 348 p. 125 illus., 100 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSpringer Optimization and Its Applications,
_x1931-6836 ;
_v174
505 0 _a1. Introduction -- 2. Synthetic data for basic computer vision problems -- 3. Synthetic simulated environments -- 4. Synthetic data outside computer vision -- 5. Directions in synthetic data development -- 6. Synthetic-to-real domain adaptation and refinement -- 7. Privacy guarantees in synthetic data -- 8. Promising directions for future work -- Conclusion -- References.
520 _aThis is the first book on synthetic data for deep learning, and its breadth of coverage may render this book as the default reference on synthetic data for years to come. The book can also serve as an introduction to several other important subfields of machine learning that are seldom touched upon in other books. Machine learning as a discipline would not be possible without the inner workings of optimization at hand. The book includes the necessary sinews of optimization though the crux of the discussion centers on the increasingly popular tool for training deep learning models, namely synthetic data. It is expected that the field of synthetic data will undergo exponential growth in the near future. This book serves as a comprehensive survey of the field. In the simplest case, synthetic data refers to computer-generated graphics used to train computer vision models. There are many more facets of synthetic data to consider. In the section on basic computer vision, the book discusses fundamental computer vision problems, both low-level (e.g., optical flow estimation) and high-level (e.g., object detection and semantic segmentation), synthetic environments and datasets for outdoor and urban scenes (autonomous driving), indoor scenes (indoor navigation), aerial navigation, and simulation environments for robotics. Additionally, it touches upon applications of synthetic data outside computer vision (in neural programming, bioinformatics, NLP, and more). It also surveys the work on improving synthetic data development and alternative ways to produce it such as GANs. The book introduces and reviews several different approaches to synthetic data in various domains of machine learning, most notably the following fields: domain adaptation for making synthetic data more realistic and/or adapting the models to be trained on synthetic data and differential privacy for generating synthetic data with privacy guarantees. This discussion is accompanied by an introduction into generative adversarial networks (GAN) and an introduction to differential privacy.
650 0 _aMachine learning.
650 0 _aOperations research.
650 0 _aManagement science.
650 0 _aComputer vision.
650 1 4 _aMachine Learning.
650 2 4 _aOperations Research, Management Science.
650 2 4 _aComputer Vision.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783030751777
776 0 8 _iPrinted edition:
_z9783030751791
776 0 8 _iPrinted edition:
_z9783030751807
830 0 _aSpringer Optimization and Its Applications,
_x1931-6836 ;
_v174
856 4 0 _uhttps://doi.org/10.1007/978-3-030-75178-4
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
942 _cSPRINGER
999 _c178179
_d178179