000 03990nam a22005655i 4500
001 978-981-97-2720-9
003 DE-He213
005 20251030112034.0
007 cr nn 008mamaa
008 240509s2024 si | s |||| 0|eng d
020 _a9789819727209
_9978-981-97-2720-9
024 7 _a10.1007/978-981-97-2720-9
_2doi
050 4 _aQ342
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
100 1 _aSantosh, KC.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
245 1 0 _aCracking the Machine Learning Code: Technicality or Innovation?
_h[electronic resource] /
_cby KC Santosh, Rodrigue Rizk, Siddhi K. Bajracharya.
250 _a1st ed. 2024.
264 1 _aSingapore :
_bSpringer Nature Singapore :
_bImprint: Springer,
_c2024.
300 _aXIX, 127 p. 110 illus., 103 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 _aStudies in Computational Intelligence,
_x1860-9503 ;
_v1155
505 0 _aChapter 1. Introduction -- Chapter 2. Data modalities and preprocessing -- Chapter 3. Basic building blocks: From shallow to deep -- Chapter 4. Experimental Setup -- Chapter 5: Case study: from numbers to images -- Chapter 6: Extension: Multimodal learning representation -- Chapter 7. Where is the innovation?.
520 _aEmploying off-the-shelf machine learning models is not an innovation. The journey through technicalities and innovation in the machine learning field is ongoing, and we hope this book serves as a compass, guiding the readers through the evolving landscape of artificial intelligence. It typically includes model selection, parameter tuning and optimization, use of pre-trained models and transfer learning, right use of limited data, model interpretability and explainability, feature engineering and autoML robustness and security, and computational cost – efficiency and scalability. Innovation in building machine learning models involves a continuous cycle of exploration, experimentation, and improvement, with a focus on pushing the boundaries of what is achievable while considering ethical implications and real-world applicability. The book is aimed at providing a clear guidance that one should not be limited to building pre-trained models to solve problems using the off-the-self basic building blocks. With primarily three different data types: numerical, textual, and image data, we offer practical applications such as predictive analysis for finance and housing, text mining from media/news, and abnormality screening for medical imaging informatics. To facilitate comprehension and reproducibility, authors offer GitHub source code encompassing fundamental components and advanced machine learning tools.
650 0 _aComputational intelligence.
_964052
650 0 _aMachine learning.
_955059
650 0 _aArtificial intelligence
_xData processing.
650 1 4 _aComputational Intelligence.
_964052
650 2 4 _aMachine Learning.
_955059
650 2 4 _aData Science.
700 1 _aRizk, Rodrigue.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_976591
700 1 _aBajracharya, Siddhi K.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_976592
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9789819727193
776 0 8 _iPrinted edition:
_z9789819727216
776 0 8 _iPrinted edition:
_z9789819727223
830 0 _aStudies in Computational Intelligence,
_x1860-9503 ;
_v1155
_968854
856 4 0 _uhttps://doi.org/10.1007/978-981-97-2720-9
912 _aZDB-2-INR
912 _aZDB-2-SXIT
999 _c59746
_d59746