000 05424nam a22005775i 4500
001 978-3-031-39477-5
003 DE-He213
005 20240730170609.0
007 cr nn 008mamaa
008 231201s2024 sz | s |||| 0|eng d
020 _a9783031394775
_9978-3-031-39477-5
024 7 _a10.1007/978-3-031-39477-5
_2doi
050 4 _aQ336
072 7 _aUN
_2bicssc
072 7 _aCOM021000
_2bisacsh
072 7 _aUN
_2thema
082 0 4 _a005.7
_223
100 1 _aFriedland, Gerald.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_994503
245 1 0 _aInformation-Driven Machine Learning
_h[electronic resource] :
_bData Science as an Engineering Discipline /
_cby Gerald Friedland.
250 _a1st ed. 2024.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2024.
300 _aXXII, 267 p. 50 illus., 33 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
505 0 _aPreface -- 1 Introduction -- 2 The Automated Scientific Process -- 3 The (Black Box) Machine Learning Process -- 4 Information Theory -- 5 Capacity -- 6 The Mechanics of Generalization -- 7 Meta-Math: Exploring the Limits of Modeling -- 8 Capacity of Neural Networks -- 8 Capacity of Neural Networks -- 10 Capacities of some other Machine Learning Methods -- 11 Data Collection and Preparation -- 12 Measuring Data Sufficiency -- 13 Machine Learning Operations -- 14 Explainability -- 15 Repeatability and Reproducibility -- 16 The Curse of Training and the Blessing of High Dimensionality -- 16 The Curse of Training and the Blessing of High Dimensionality -- Appendix A Recap: The Logarithm -- Appendix B More on Complexity -- Appendix C Concepts Cheat Sheet -- Appendix D A Review Form that Promotes Reproducibility -- List of Illustrations -- Bibliography.
520 _aThis groundbreaking book transcends traditional machine learning approaches by introducing information measurement methodologies that revolutionize the field. Stemming from a UC Berkeley seminar on experimental design for machine learning tasks, these techniques aim to overcome the 'black box' approach of machine learning by reducing conjectures such as magic numbers (hyper-parameters) or model-type bias. Information-based machine learning enables data quality measurements, a priori task complexity estimations, and reproducible design of data science experiments. The benefits include significant size reduction, increased explainability, and enhanced resilience of models, all contributing to advancing the discipline's robustness and credibility. While bridging the gap between machine learning and disciplines such as physics, information theory, and computer engineering, this textbook maintains an accessible and comprehensive style, making complex topics digestible for abroad readership. Information-Driven Machine Learning explores the synergistic harmony among these disciplines to enhance our understanding of data science modeling. Instead of solely focusing on the "how," this text provides answers to the "why" questions that permeate the field, shedding light on the underlying principles of machine learning processes and their practical implications. By advocating for systematic methodologies grounded in fundamental principles, this book challenges industry practices that have often evolved from ideologic or profit-driven motivations. It addresses a range of topics, including deep learning, data drift, and MLOps, using fundamental principles such as entropy, capacity, and high dimensionality. Ideal for both academia and industry professionals, this textbook serves as a valuable tool for those seeking to deepen their understanding of data science as an engineering discipline. Its thought-provoking content stimulates intellectual curiosity and caters to readers who desire more than just code or ready-made formulas. The text invites readers to explore beyond conventional viewpoints, offering an alternative perspective that promotes a big-picture view for integrating theory with practice. Suitable for upper undergraduate or graduate-level courses, this book can also benefit practicing engineers and scientists in various disciplines by enhancing their understanding of modeling and improving data measurement effectively.
650 0 _aArtificial intelligence
_xData processing.
_921787
650 0 _aMachine learning.
_91831
650 0 _aData structures (Computer science).
_98188
650 0 _aInformation theory.
_914256
650 0 _aExpert systems (Computer science).
_93392
650 0 _aArtificial intelligence.
_93407
650 1 4 _aData Science.
_934092
650 2 4 _aMachine Learning.
_91831
650 2 4 _aData Structures and Information Theory.
_931923
650 2 4 _aKnowledge Based Systems.
_979172
650 2 4 _aArtificial Intelligence.
_93407
710 2 _aSpringerLink (Online service)
_994508
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031394768
776 0 8 _iPrinted edition:
_z9783031394782
776 0 8 _iPrinted edition:
_z9783031394799
856 4 0 _uhttps://doi.org/10.1007/978-3-031-39477-5
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
942 _cEBK
999 _c87068
_d87068