Mathematical pictures at a data science exhibition (Record no. 825)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 03821nam a2200205Ia 4500 |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20250409102005.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 230421s2022||||xx |||||||||||||| ||eng|| |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER | |
| ISBN | 9781009001854 |
| 041 ## - LANGUAGE CODE | |
| Language code of text/sound track or separate title | English |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 005.7 F68 |
| 100 ## - MAIN ENTRY--AUTHOR NAME | |
| Personal name | Foucart, Simon |
| Relator term | Author |
| 245 #0 - TITLE STATEMENT | |
| Title | Mathematical pictures at a data science exhibition |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Place of publication | United Kingdom: |
| Name of publisher | Cambridge University Press, |
| Year of publication | 2022. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Number of Pages | xx, 318p.; 22cms. |
| 500 ## - GENERAL NOTE | |
| General note | This text provides deep and comprehensive coverage of the mathematical background for data science, including machine learning, optimal recovery, compressed sensing, optimization, and neural networks. In the past few decades, heuristic methods adopted by big tech companies have complemented existing scientific disciplines to form the new field of Data Science. This text embarks the readers on an engaging itinerary through the theory supporting the field. Altogether, twenty-seven lecture-length chapters with exercises provide all the details necessary for a solid understanding of key topics in data science. While the book covers standard material on machine learning and optimization, it also includes distinctive presentations of topics such as reproducing kernel Hilbert spaces, spectral clustering, optimal recovery, compressed sensing, group testing, and applications of semidefinite programming. Students and data scientists with less mathematical background will appreciate the appendices that provide more background on some of the more abstract concepts.<br/><br/>Specially designed for mathematicians and graduate students in mathematics who want to learn more about data science<br/>Presents a broad view of mathematical data science by including a wide variety of subjects, from the very popular subject of machine learning to the lesser-known subject of optimal recovery<br/>Proves at least one theoretical result in each chapter, helping the reader develop a sound understanding of topics explained with detailed arguments<br/>Includes original content that has never been published before in book form, such as the presentation of compressive sensing through a nonstandard restricted isometry property<br/>Provides background for some of the more abstract concepts in the appendices<br/>Author's GitHub page includes computational illustrations made in MATLAB and Python to demonstrate how the theory is applied<br/><br/>Part I. Machine Learning:<br/><br/>1. Rudiments of Statistical Learning<br/>2. Vapnik–Chervonenkis Dimension<br/>3. Learnability for Binary Classification<br/>4. Support Vector Machines<br/>5. Reproducing Kernel Hilbert<br/>6. Regression and Regularization<br/>7. Clustering<br/>8. Dimension Reduction<br/>Part II Optimal Recovery:<br/>9. Foundational Results of Optimal Recovery<br/>10. Approximability Models<br/>11. Ideal Selection of Observation Schemes<br/>12. Curse of Dimensionality<br/>13. Quasi-Monte Carlo Integration<br/>Part III Compressive Sensing:<br/>14. Sparse Recovery from Linear Observations<br/>15. The Complexity of Sparse Recovery<br/>16. Low-Rank Recovery from Linear Observations<br/>17. Sparse Recovery from One-Bit Observations<br/>18. Group Testing<br/>Part IV Optimization:<br/>19. Basic Convex Optimization<br/>20. Snippets of Linear Programming<br/>21. Duality Theory and Practice<br/>22. Semidefinite Programming in Action<br/>23. Instances of Nonconvex Optimization<br/>Part V Neural Networks:<br/>24. First Encounter with ReLU Networks<br/>25. Expressiveness of Shallow Networks<br/>26. Various Advantages of Depth<br/>27. Tidbits on Neural Network Training<br/>Appendix A<br/>High-Dimensional Geometry<br/>Appendix B. Probability Theory<br/>Appendix C. Functional Analysis<br/>Appendix D. Matrix Analysis<br/>Appendix E. Approximation Theory |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical Term | Computer science |
| General subdivision | Mathematics |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical Term | Compressed sensing, optimization, and neural networks |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical Term | Rudiments of Statistical Learning |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Books |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) | |
| -- | P29.99 |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) | |
| -- | P29.99 |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) | |
| -- | P29.99 |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) | |
| -- | P29.99 |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) | |
| -- | P29.99 |
| Withdrawn status | Lost status | Damaged status | Not for loan | Permanent Location | Current Location | Shelving location | Full call number | Accession Number | Copy number | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|
| Dr. S. R. Ranganathan Library | Dr. S. R. Ranganathan Library | General Stacks | 005.7 F68 | 2811 | 1 | Books | ||||
| Dr. S. R. Ranganathan Library | Dr. S. R. Ranganathan Library | General Stacks | 005.7 F68:1 | 2812 | 2 | Books | ||||
| Dr. S. R. Ranganathan Library | Dr. S. R. Ranganathan Library | General Stacks | 005.7 F68:2 | 2813 | 3 | Books | ||||
| Dr. S. R. Ranganathan Library | Dr. S. R. Ranganathan Library | General Stacks | 005.7 F68:3 | 2814 | 4 | Books | ||||
| Dr. S. R. Ranganathan Library | Dr. S. R. Ranganathan Library | General Stacks | 005.7 F68:4 | 2815 | 5 | Books |