Statistical Machine Learning: A Unified Framework: Chapman & Hall/CRC Texts in Statistical Science
Autor Richard Goldenen Limba Engleză Hardback – 2 iul 2020
Features:
- Unified empirical risk minimization framework supports rigorous mathematical analyses of widely used supervised, unsupervised, and reinforcement machine learning algorithms
- Matrix calculus methods for supporting machine learning analysis and design applications
- Explicit conditions for ensuring convergence of adaptive, batch, minibatch, MCEM, and MCMC learning algorithms that minimize both unimodal and multimodal objective functions
- Explicit conditions for characterizing asymptotic properties of M-estimators and model selection criteria such as AIC and BIC in the presence of possible model misspecification
About the Author:
Richard M. Golden (Ph.D., M.S.E.E., B.S.E.E.) is Professor of Cognitive Science and Participating Faculty Member in Electrical Engineering at the University of Texas at Dallas. Dr. Golden has published articles and given talks at scientific conferences on a wide range of topics in the fields of both statistics and machine learning over the past three decades. His long-term research interests include identifying conditions for the convergence of deterministic and stochastic machine learning algorithms and investigating estimation and inference in the presence of possibly misspecified probability models.
Din seria Chapman & Hall/CRC Texts in Statistical Science
- 5% Preț: 635.71 lei
- 8% Preț: 572.20 lei
- 9% Preț: 617.40 lei
- 8% Preț: 552.91 lei
- 9% Preț: 595.00 lei
- Preț: 356.63 lei
- 8% Preț: 570.43 lei
- 9% Preț: 681.68 lei
- 9% Preț: 602.05 lei
- 8% Preț: 551.97 lei
- 9% Preț: 1260.30 lei
- 9% Preț: 613.84 lei
- 5% Preț: 374.41 lei
- 9% Preț: 600.69 lei
- 8% Preț: 444.23 lei
- 8% Preț: 547.27 lei
- 8% Preț: 544.47 lei
- 8% Preț: 548.93 lei
- Preț: 356.63 lei
- 8% Preț: 496.94 lei
- 9% Preț: 608.07 lei
- 8% Preț: 419.81 lei
- 9% Preț: 610.93 lei
- 20% Preț: 508.92 lei
- 9% Preț: 608.07 lei
- 8% Preț: 496.37 lei
- Preț: 357.59 lei
- 8% Preț: 547.09 lei
- Preț: 341.42 lei
- 8% Preț: 548.14 lei
- 9% Preț: 772.11 lei
- Preț: 348.11 lei
- 8% Preț: 549.91 lei
- 8% Preț: 444.54 lei
- 9% Preț: 641.60 lei
- Preț: 389.37 lei
- Preț: 349.09 lei
- Preț: 316.73 lei
- Preț: 341.85 lei
- Preț: 349.09 lei
- 9% Preț: 595.90 lei
- 9% Preț: 593.60 lei
- 9% Preț: 599.55 lei
- 11% Preț: 671.27 lei
- 8% Preț: 510.12 lei
- 8% Preț: 511.06 lei
- 8% Preț: 563.39 lei
Preț: 645.07 lei
Preț vechi: 829.98 lei
-22% Nou
Puncte Express: 968
Preț estimativ în valută:
123.45€ • 128.24$ • 102.55£
123.45€ • 128.24$ • 102.55£
Carte tipărită la comandă
Livrare economică 03-17 februarie 25
Preluare comenzi: 021 569.72.76
Specificații
ISBN-13: 9781138484696
ISBN-10: 1138484695
Pagini: 524
Dimensiuni: 178 x 254 x 32 mm
Greutate: 3.17 kg
Ediția:1
Editura: CRC Press
Colecția Chapman and Hall/CRC
Seria Chapman & Hall/CRC Texts in Statistical Science
ISBN-10: 1138484695
Pagini: 524
Dimensiuni: 178 x 254 x 32 mm
Greutate: 3.17 kg
Ediția:1
Editura: CRC Press
Colecția Chapman and Hall/CRC
Seria Chapman & Hall/CRC Texts in Statistical Science
Cuprins
Part I: Inference and Learning Machines. 1. A Statistical Machine Learning Framework 2. Set Theory for Concept Modeling 3. Formal Machine Learning Algorithms Part II: Deterministic Learning Machines 4. Linear Algebra for Machine Learning 5. Matrix Calculus for Machine Learning 6. Convergence of Time-Invariant Dynamical Systems 7. Batch Learning Algorithm Convergence Part III: Stochastic Learning Machines 8. Random Vectors and Random Functions 9. Stochastic Sequences 10. Probability Models of Data Generation 11. Monte Carlo Markov Chain Algorithm Convergence 12. Adaptive Learning Algorithm Convergence Part IV: Generalization Performance 13. Statistical Learning Objective Function Design 14. Simulation Methods for Evaluating Generalization 15. Analytic Formulas for Evaluating Generalization 16. Model Selection and Evaluation
Notă biografică
Richard M. Golden (Ph.D., M.S.E.E., B.S.E.E.) is Professor of Cognitive Science and Participating Faculty Member in Electrical Engineering at the University of Texas at Dallas. Dr. Golden has published articles and given talks at scientific conferences on a wide range of topics in the fields of both statistics and machine learning over the past three decades. His long-term research interests include identifying conditions for the convergence of deterministic and stochastic machine learning algorithms and investigating estimation and inference in the presence of possibly misspecified probability models.
Recenzii
'In summary, readers of this book need to have fair knowledge of statistics, computer science, electrical engineering, or applied mathematics. However, practicing professional engineers and scientists may find the material in this book to be a useful reference for verifying sufficient conditions for ensuring convergence of many commonly used deterministic and stochastic machine learning optimization algorithms; and for ensuring correct usage of commonly used statistical tools for characterizing sampling error and generalization performance. Further, since this book includes a large number of examples, teachers of a course on machine learning may also find this book useful. In addition, applied researchers involved with machine learning may also find this book helpful.'
- Sada Nand Dwivedi, International Society for Clinical Biostatistics, 71, 2021
- Sada Nand Dwivedi, International Society for Clinical Biostatistics, 71, 2021
Descriere
This book is a text intended for advanced undergraduates or graduate students which provides theoretical tools for analyzing and designing a large class of supervised, unsupervised, and reinforcement statistical machine learning algorithms using classical theorems from the fields of nonlinear optimization theory and mathematical statistics.