000 04211nam a22005895i 4500
001 978-3-030-90987-1
003 DE-He213
005 20240423125546.0
007 cr nn 008mamaa
008 220426s2022 sz | s |||| 0|eng d
020 _a9783030909871
_9978-3-030-90987-1
024 7 _a10.1007/978-3-030-90987-1
_2doi
050 4 _aTA1634
072 7 _aUYQV
_2bicssc
072 7 _aCOM016000
_2bisacsh
072 7 _aUYQV
_2thema
082 0 4 _a006.37
_223
100 1 _aBetti, Alessandro.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
245 1 0 _aDeep Learning to See
_h[electronic resource] :
_bTowards New Foundations of Computer Vision /
_cby Alessandro Betti, Marco Gori, Stefano Melacci.
250 _a1st ed. 2022.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2022.
300 _aXIV, 105 p. 13 illus., 3 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 _aSpringerBriefs in Computer Science,
_x2191-5776
505 0 _a1. Introduction -- 2. Cutting the Umbilical Cord with Pattern Recognition -- 3. Spatiotemporal Visual Environments -- 4. Hierarchical Description of Visual Tasks -- 5. Benchmarks and the “En Plein Air” Challenge.
520 _aThe remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this book criticizes the supposed scientific progress in the field, and proposes the investigation of vision within the framework of information-based laws of nature. Specifically, the present work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms, and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal. Topics and features: Presents a curiosity-driven approach, posing questions to stimulate readers to design novel computational models of vision Offers a rethinking of computer vision, arguing for an approach based on vision in nature, versus regarding visual signals as collections of images Provides an interdisciplinary commentary, aiming to unify computer vision, machine learning, human vision, and computational neuroscience Serving to inspire and stimulate critical reflection and discussion, yet requiring no prior advanced technical knowledge, the text can naturally be paired with classic textbooks on computer vision to better frame the current state of the art, open problems, and novel potential solutions. This unique volume will be of great benefit to graduate and advanced undergraduate students in computer science, computational neuroscience, physics, and other related disciplines.
650 0 _aComputer vision.
650 0 _aMachine learning.
650 0 _aComputational neuroscience.
650 0 _aColor.
650 0 _aVision.
650 1 4 _aComputer Vision.
650 2 4 _aMachine Learning.
650 2 4 _aComputational Neuroscience.
650 2 4 _aVision and Colour Science.
700 1 _aGori, Marco.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
700 1 _aMelacci, Stefano.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783030909864
776 0 8 _iPrinted edition:
_z9783030909888
830 0 _aSpringerBriefs in Computer Science,
_x2191-5776
856 4 0 _uhttps://doi.org/10.1007/978-3-030-90987-1
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
942 _cSPRINGER
999 _c179275
_d179275