Interpretable Machine Learning (Record no. 359833)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 04460 a2200169 4500 |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20241018124752.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 241018b |||||||| |||| 00| 0 eng d |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER | |
| International Standard Book Number | 9789355428370 |
| 041 ## - LANGUAGE CODE | |
| Language code of text/sound track or separate title | English |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Author | Molnar C. |
| 245 ## - TITLE STATEMENT | |
| Title | Interpretable Machine Learning |
| Remainder of title | :A Guide For Making Black Box Models Explainable |
| 250 ## - EDITION STATEMENT | |
| Edition statement | 2nd |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Name of publisher, distributor, etc. | SPD |
| Date of publication, distribution, etc. | 2024 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 317 |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Contents<br/>Preface by the Author ix<br/>1 Introduction 1<br/>1.1 Story Time . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3<br/>1.2 What Is Machine Learning? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9<br/>1.3 Terminology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10<br/>2 Interpretability 13<br/>2.1 Importance of Interpretability . . . . . . . . . . . . . . . . . . . . . . . . . . . 13<br/>2.2 Taxonomy of Interpretability Methods . . . . . . . . . . . . . . . . . . . . . . 18<br/>2.3 Scope of Interpretability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20<br/>2.4 Evaluation of Interpretability . . . . . . . . . . . . . . . . . . . . . . . . . . . 22<br/>2.5 Properties of Explanations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22<br/>2.6 Human-friendly Explanations . . . . . . . . . . . . . . . . . . . . . . . . . . . 25<br/>3 Datasets 31<br/>3.1 Bike Rentals (Regression) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31<br/>3.2 YouTube Spam Comments (Text Classification) . . . . . . . . . . . . . . . . . 32<br/>3.3 Risk Factors for Cervical Cancer (Classification) . . . . . . . . . . . . . . . . 33<br/>4 Interpretable Models 35<br/>4.1 Linear Regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37<br/>4.2 Logistic Regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53<br/>4.3 GLM, GAM and more . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59<br/>4.4 Decision Tree . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77<br/>4.5 Decision Rules . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83<br/>4.6 RuleFit . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 99<br/>4.7 Other Interpretable Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . 107<br/>5 Model-Agnostic Methods 109<br/>6 Example-Based Explanations 113<br/>7 Global Model-Agnostic Methods 115<br/>7.1 Partial Dependence Plot (PDP) . . . . . . . . . . . . . . . . . . . . . . . . . . 116<br/>7.2 Accumulated Local Effects (ALE) Plot . . . . . . . . . . . . . . . . . . . . . . 122<br/>7.3 Feature Interaction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 140<br/>7.4 Functional Decomposition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 147<br/>v<br/>vi Contents<br/>7.5 Permutation Feature Importance . . . . . . . . . . . . . . . . . . . . . . . . . 157<br/>7.6 Global Surrogate . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 165<br/>7.7 Prototypes and Criticisms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 170<br/>8 Local Model-Agnostic Methods 179<br/>8.1 Individual Conditional Expectation (ICE) . . . . . . . . . . . . . . . . . . . . 180<br/>8.2 Local Surrogate (LIME) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 185<br/>8.3 Counterfactual Explanations . . . . . . . . . . . . . . . . . . . . . . . . . . . 194<br/>8.4 Scoped Rules (Anchors) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205<br/>8.5 Shapley Values . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 215<br/>8.6 SHAP (SHapley Additive exPlanations) . . . . . . . . . . . . . . . . . . . . . 227<br/>9 Neural Network Interpretation 241<br/>9.1 Learned Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 243<br/>9.2 Pixel Attribution (Saliency Maps) . . . . . . . . . . . . . . . . . . . . . . . . 254<br/>9.3 Detecting Concepts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 265<br/>9.4 Adversarial Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 270<br/>9.5 Influential Instances . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279<br/>10 A Look into the Crystal Ball 295<br/>10.1 The Future of Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . 296<br/>10.2 The Future of Interpretability . . . . . . . . . . . . . . . . . . . . . . . . . . . 298<br/>11 Contribute to the Book 301<br/>12 Citing this Book 303<br/>13 Translations 305<br/>14 Acknowledgements 307 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Books |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Date acquired | Vendor | Net Price | Total Checkouts | Full call number | Barcode | Date last seen | Actual Price | Bill Date | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | Cummins College of Engineering for Women Pune | Cummins College of Engineering for Women Pune | 11/10/2024 | 115 | 1087.50 | 006.31 MOL | CCEP-BK-67497 | 11/10/2024 | 1450.00 | 11/10/2024 | Books |