000 03285nam a22005415i 4500
001 978-3-031-14595-7
003 DE-He213
005 20240730164430.0
007 cr nn 008mamaa
008 221008s2022 sz | s |||| 0|eng d
020 _a9783031145957
_9978-3-031-14595-7
024 7 _a10.1007/978-3-031-14595-7
_2doi
050 4 _aTA1634
072 7 _aUYQV
_2bicssc
072 7 _aCOM016000
_2bisacsh
072 7 _aUYQV
_2thema
082 0 4 _a006.37
_223
100 1 _aHuang, Lei.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_984488
245 1 0 _aNormalization Techniques in Deep Learning
_h[electronic resource] /
_cby Lei Huang.
250 _a1st ed. 2022.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2022.
300 _aXI, 110 p. 26 illus., 21 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 _aSynthesis Lectures on Computer Vision,
_x2153-1064
505 0 _aIntroduction -- Motivation and Overview of Normalization in DNNs -- A General View of Normalizing Activations -- A Framework for Normalizing Activations as Functions -- Multi-Mode and Combinational Normalization -- BN for More Robust Estimation -- Normalizing Weights -- Normalizing Gradients -- Analysis of Normalization -- Normalization in Task-specific Applications -- Summary and Discussion.
520 _aThis book presents and surveys normalization techniques with a deep analysis in training deep neural networks. In addition, the author provides technical details in designing new normalization methods and network architectures tailored to specific tasks. Normalization methods can improve the training stability, optimization efficiency, and generalization ability of deep neural networks (DNNs) and have become basic components in most state-of-the-art DNN architectures. The author provides guidelines for elaborating, understanding, and applying normalization methods. This book is ideal for readers working on the development of novel deep learning algorithms and/or their applications to solve practical problems in computer vision and machine learning tasks. The book also serves as a resource researchers, engineers, and students who are new to the field and need to understand and train DNNs.
650 0 _aComputer vision.
_984489
650 0 _aArtificial intelligence.
_93407
650 0 _aNeural networks (Computer science) .
_984490
650 0 _aMachine learning.
_91831
650 1 4 _aComputer Vision.
_984491
650 2 4 _aArtificial Intelligence.
_93407
650 2 4 _aMathematical Models of Cognitive Processes and Neural Networks.
_932913
650 2 4 _aMachine Learning.
_91831
710 2 _aSpringerLink (Online service)
_984496
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031145940
776 0 8 _iPrinted edition:
_z9783031145964
776 0 8 _iPrinted edition:
_z9783031145971
830 0 _aSynthesis Lectures on Computer Vision,
_x2153-1064
_984498
856 4 0 _uhttps://doi.org/10.1007/978-3-031-14595-7
912 _aZDB-2-SXSC
942 _cEBK
999 _c85673
_d85673