Practical Explainable AI Using Python - Artificial Intelligence Model Explanations Using Python-Based Libraries, Extensions, and Frameworks
Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as...
Saved in:
| Main Author | |
|---|---|
| Format | eBook Book |
| Language | English |
| Published |
Berkeley, CA
Apress, an imprint of Springer Nature
2022
Apress Apress L. P |
| Edition | 1 |
| Subjects | |
| Online Access | Get full text |
| ISBN | 1484271572 9781484271575 9781484271582 1484271580 |
| DOI | 10.1007/978-1-4842-7158-2 |
Cover
| Abstract | Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers. You'll begin with an introduction to model explainability and interpretability basics, ethical consideration, and biases in predictions generated by AI models. Next, you'll look at methods and systems to interpret linear, non-linear, and time-series models used in AI. The book will also cover topics ranging from interpreting to understanding how an AI algorithm makes a decision. Further, you will learn the most complex ensemble models, explainability, and interpretability using frameworks such as Lime, SHAP, Skater, ELI5, etc. Moving forward, you will be introduced to model explainability for unstructured data, classification problems, and natural language processing-related tasks. |
|---|---|
| AbstractList | Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers.You'll begin with an introduction to model explainability and interpretability basics, ethical consideration, and biases in predictions generated by AI models. Next, you'll look at methods and systems to interpret linear, non-linear, and time-series models used in AI. The book will also cover topics ranging from interpreting to understanding how an AI algorithm makes a decisionFurther, you will learn the most complex ensemble models, explainability, and interpretability using frameworks such as Lime, SHAP, Skater, ELI5, etc. Moving forward, youwill be introduced to model explainability for unstructured data, classification problems, and natural language processing–related tasks. Additionally, the book looks at counterfactual explanations for AI models. Practical Explainable AI Using Python shines the light on deep learning models, rule-based expert systems, and computer vision tasks using various XAI frameworks.What You'll LearnReview the different ways of making an AI model interpretable and explainableExamine the biasness and good ethical practices of AI modelsQuantify, visualize, and estimate reliability of AI modelsDesign frameworks to unbox the black-box modelsAssess the fairness of AI modelsUnderstand the building blocks of trust in AI modelsIncrease the level of AI adoptionWho This Book Is ForAI engineers, data scientists, and software developers involved in driving AI projects/ AI products. Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers.You'll begin with an introduction to model explainability and interpretability basics, ethical consideration, and biases in predictions generated by AI models. Next, you'll look at methods and systems to interpret linear, non-linear, and time-series models used in AI. The book will also cover topics ranging from interpreting to understanding how an AI algorithm makes a decisionFurther, you will learn the most complex ensemble models, explainability, and interpretability using frameworks such as Lime, SHAP, Skater, ELI5, etc. Moving forward, you will be introduced to model explainability for unstructured data, classification problems, and natural language processing-related tasks. Additionally, the book looks at counterfactual explanations for AI models. Practical Explainable AI Using Python shines the light on deep learning models, rule-based expert systems, and computer vision tasks using various XAI frameworks.What You'll LearnReview the different ways of making an AI model interpretable and explainableExamine the biasness and good ethical practices of AI modelsQuantify, visualize, and estimate reliability of AI modelsDesign frameworks to unbox the black-box modelsAssess the fairness of AI modelsUnderstand the building blocks of trust in AI modelsIncrease the level of AI adoptionWho This Book Is ForAI engineers, data scientists, and software developers involved in driving AI projects/ AI products. Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers. You'll begin with an introduction to model explainability and interpretability basics, ethical consideration, and biases in predictions generated by AI models. Next, you'll look at methods and systems to interpret linear, non-linear, and time-series models used in AI. The book will also cover topics ranging from interpreting to understanding how an AI algorithm makes a decision Further, you will learn the most complex ensemble models, explainability, and interpretability using frameworks such as Lime, SHAP, Skater, ELI5, etc. Moving forward, youwill be introduced to model explainability for unstructured data, classification problems, and natural language processing–related tasks. Additionally, the book looks at counterfactual explanations for AI models. Practical Explainable AI Using Python shines the light on deep learning models, rule-based expert systems, and computer vision tasks using various XAI frameworks. What You'll Learn * Review the different ways of making an AI model interpretable and explainable * Examine the biasness and good ethical practices of AI models * Quantify, visualize, and estimate reliability of AI models * Design frameworks to unbox the black-box models * Assess the fairness of AI models * Understand the building blocks of trust in AI models * Increase the level of AI adoption Who This Book Is For AI engineers, data scientists, and software developers involved in driving AI projects/ AI products. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers. -- Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers. You'll begin with an introduction to model explainability and interpretability basics, ethical consideration, and biases in predictions generated by AI models. Next, you'll look at methods and systems to interpret linear, non-linear, and time-series models used in AI. The book will also cover topics ranging from interpreting to understanding how an AI algorithm makes a decision. Further, you will learn the most complex ensemble models, explainability, and interpretability using frameworks such as Lime, SHAP, Skater, ELI5, etc. Moving forward, you will be introduced to model explainability for unstructured data, classification problems, and natural language processing-related tasks. |
| Author | Mishra, Pradeepta |
| Author_xml | – sequence: 1 fullname: Mishra, Pradeepta |
| BackLink | https://cir.nii.ac.jp/crid/1130853708031233289$$DView record in CiNii |
| BookMark | eNplkc1u1DAUhYP4EbTMAyCxyAJUITXUP-PYWaajKYw0iFlQtpaTXE9NXHtqh2n7DH1pnJksQGxsXd_vnGsfn2QvnHeQZe8w-owR4hcVFwUu5mJOCo6ZKMizbJbOMCMUMyS4eJ6d4LGdupy8SgWpMMWCEfQ6m8X4CyFEOClLTt9kT5ug2sG0yubLh51VxqnGQl6v8uto3DbfPA433uVFXofBaNOaBK7cANaaLbgW8m--g0nr1GC8i_8oi0sVocvXpgkqGIjnCR3AxRE8z5Xr8qugbuHehz6-zV5qZSPMpv00-3m1_LH4Wqy_f1kt6nWhyJwhVhDNiUJYdLwTABoxJUrUdpQ0ZSoIVm0Dpa6AMgyItk3Zad0I0vBKA9Eto6fZ2dE49sba6PUgG-_7SOYPXDZ9TAGlYEtGE_npSKrYw3288XaIcm_hgMsx9SloQRJ7MbnuQgoAwtFUYiTHfxtpieXIy1EgR8WHSaF0Smfi9-Q_4-m6u-DvfkMc5GF-C24Iysrl5aIUVLCySuT7iYRgYesnxznDtEJ_zXPGyNaMK8YUCUY5EohiQikRo8vHI9Y7vwcr03NuVXg8mMl-t1nWq-tNTegfTj3C0w |
| ContentType | eBook Book |
| Copyright | 2022 Pradeepta Mishra 2022 |
| Copyright_xml | – notice: 2022 – notice: Pradeepta Mishra 2022 |
| DBID | RYH YSPEL OHILO OODEK |
| DEWEY | 006.3 |
| DOI | 10.1007/978-1-4842-7158-2 |
| DatabaseName | CiNii Complete Perlego O'Reilly Online Learning: Corporate Edition O'Reilly Online Learning: Academic/Public Library Edition |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISBN | 9781523150878 1523150874 9781484271582 1484271580 |
| Edition | 1 |
| ExternalDocumentID | bks000158653 9781484271582 506619 EBC6838569 4513902 BC11155459 book_kpPEAIUPA2 |
| Genre | Electronic books |
| GroupedDBID | 38. AABBV AADCS AAJNZ AALIM AAQFW AAZWU ABSVR ABTHU ACBPT ACPMC ACXXF ADNVS AEKFX AIYYB ALMA_UNASSIGNED_HOLDINGS BBABE CMZ CZZ DYXOI IEZ K-E KT4 OHILO OODEK SBO TD3 TPJZQ WZT YSPEL Z5O Z7R Z7S Z7U Z7V Z7W Z7X Z7Y Z7Z Z81 Z82 Z83 Z84 Z85 Z87 Z88 ACBYE AJIEK RYH |
| ID | FETCH-LOGICAL-a24505-2f72a018d7d8eef05a860cd32b6f0521acbe6f9e351e03cb6dffb82b79fe2fc53 |
| IEDL.DBID | K-E |
| ISBN | 1484271572 9781484271575 9781484271582 1484271580 |
| IngestDate | Tue Oct 28 12:08:37 EDT 2025 Fri Nov 08 03:35:23 EST 2024 Tue Jul 29 20:26:24 EDT 2025 Sat Oct 25 00:26:58 EDT 2025 Fri May 30 22:58:15 EDT 2025 Tue Sep 30 15:18:00 EDT 2025 Mon Aug 25 08:57:45 EDT 2025 Sat Nov 23 14:02:06 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | false |
| LCCallNum | QA76.73.P98 .M57 2021 |
| LCCallNum_Ident | Q334-342 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a24505-2f72a018d7d8eef05a860cd32b6f0521acbe6f9e351e03cb6dffb82b79fe2fc53 |
| Notes | index: p. 335-344 |
| OCLC | 1291318520 |
| PQID | EBC6838569 |
| PageCount | 356 |
| ParticipantIDs | skillsoft_books24x7_bks000158653 askewsholts_vlebooks_9781484271582 springer_books_10_1007_978_1_4842_7158_2 safari_books_v2_9781484271582 proquest_ebookcentral_EBC6838569 perlego_books_4513902 nii_cinii_1130853708031233289 knovel_primary_book_kpPEAIUPA2 |
| PublicationCentury | 2000 |
| PublicationDate | 2022 2021 2021-12-14T00:00:00 20211215 2021-12-14 2021. |
| PublicationDateYYYYMMDD | 2022-01-01 2021-01-01 2021-12-14 2021-12-15 |
| PublicationDate_xml | – year: 2022 text: 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | Berkeley, CA |
| PublicationPlace_xml | – name: New York – name: Berkeley, CA – name: Place of publication not identified |
| PublicationYear | 2022 2021 |
| Publisher | Apress, an imprint of Springer Nature Apress Apress L. P |
| Publisher_xml | – name: Apress, an imprint of Springer Nature – name: Apress – name: Apress L. P |
| SSID | ssj0002726673 |
| Score | 2.3437681 |
| Snippet | Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called... This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using... |
| SourceID | skillsoft askewsholts springer safari proquest perlego nii knovel |
| SourceType | Aggregation Database Publisher |
| SubjectTerms | Artificial Intelligence Computer games Computer programming Computer Science COMPUTERS General Engineering & Project Administration General References Professional and Applied Computing Programming Python Python (Computer program language) Software Engineering |
| SubjectTermsDisplay | Computer games -- Programming. Computer programming. Electronic books. Python (Computer program language) |
| TableOfContents | Title Page
Introduction
Table of Contents
1. Model Explainability and Interpretability
2. AI Ethics, Biasness, and Reliability
3. Explainability for Linear Models
4. Explainability for Non-Linear Models
5. Explainability for Ensemble Models
6. Explainability for Time Series Models
7. Explainability for NLP
8. AI Model Fairness Using a What-if Scenario
9. Explainability for Deep Learning Models
10. Counterfactual Explanations for XAI Models
11. Contrastive Explanations for Machine Learning
12. Model-Agnostic Explanations by Identifying Prediction Invariance
13. Model Explainability for Rule-Based Expert Systems
14. Model Explainability for Computer Vision
Index Using SHAP Multiclass Categorical Boosting Model -- Using SHAP for Light GBM Model Explanation -- Conclusion -- Chapter 6: Explainability for Time Series Models -- Time Series Models -- Knowing Which Model Is Good -- Strategy for Forecasting -- Confidence Interval of Predictions -- What Happens to Trust? -- Time Series: LIME -- Conclusion -- Chapter 7: Explainability for NLP -- Natural Language Processing Tasks -- Explainability for Text Classification -- Dataset for Text Classification -- Explaining Using ELI5 -- Calculating the Feature Weights for Local Explanation -- Local Explanation Example 1 -- Local Explanation Example 2 -- Local Explanation Example 3 -- Explanation After Stop Word Removal -- N-gram-Based Text Classification -- Multi-Class Label Text Classification Explainability -- Local Explanation Example 1 -- Local Explanation Example 2 -- Local Explanation Example 1 -- Conclusion -- Chapter 8: AI Model Fairness Using a What-If Scenario -- What Is the WIT? -- Installing the WIT -- Evaluation Metric -- Conclusion -- Chapter 9: Explainability for Deep Learning Models -- Explaining DL Models -- Using SHAP with DL -- Using Deep SHAP -- Using Alibi -- SHAP Explainer for Deep Learning -- Another Example of Image Classification -- Using SHAP -- Deep Explainer for Tabular Data -- Conclusion -- Chapter 10: Counterfactual Explanations for XAI Models -- What Are CFEs? -- Implementation of CFEs -- CFEs Using Alibi -- Counterfactual for Regression Tasks -- Conclusion -- Chapter 11: Contrastive Explanations for Machine Learning -- What Is CE for ML? -- CEM Using Alibi -- Comparison of an Original Image vs. an Autoencoder-Generated Image -- CEM for Tabular Data Explanations -- Conclusion -- Chapter 12: Model-Agnostic Explanations by Identifying Prediction Invariance -- What Is Model Agnostic? -- What Is an Anchor? -- Anchor Explanations Using Alibi Anchor Text for Text Classification -- Anchor Image for Image Classification -- Conclusion -- Chapter 13: Model Explainability for Rule-Based Expert Systems -- What Is an Expert System? -- Backward and Forward Chaining -- Rule Extraction Using Scikit-Learn -- Need for a Rule-Based System -- Challenges of an Expert System -- Conclusion -- Chapter 14: Model Explainability for Computer Vision -- Why Explainability for Image Data? -- Anchor Image Using Alibi -- Integrated Gradients Method -- Conclusion -- Index Intro -- Table of Contents -- About the Author -- About the Technical Reviewers -- Acknowledgments -- Introduction -- Chapter 1: Model Explainability and Interpretability -- Establishing the Framework -- Artificial Intelligence -- Need for XAI -- Explainability vs. Interpretability -- Explainability Types -- Tools for Model Explainability -- SHAP -- LIME -- ELI5 -- Skater -- Skope_rules -- Methods of XAI for ML -- XAI Compatible Models -- XAI Meets Responsible AI -- Evaluation of XAI -- Conclusion -- Chapter 2: AI Ethics, Biasness, and Reliability -- AI Ethics Primer -- Biasness in AI -- Data Bias -- Algorithmic Bias -- Bias Mitigation Process -- Interpretation Bias -- Training Bias -- Reliability in AI -- Conclusion -- Chapter 3: Explainability for Linear Models -- Linear Models -- Linear Regression -- VIF and the Problems It Can Generate -- Final Model -- Model Explainability -- Trust in ML Model: SHAP -- Local Explanation and Individual Predictions in a ML Model -- Global Explanation and Overall Predictions in ML Model -- LIME Explanation and ML Model -- Skater Explanation and ML Model -- ELI5 Explanation and ML Model -- Logistic Regression -- Interpretation -- LIME Inference -- Conclusion -- Chapter 4: Explainability for Non-Linear Models -- Non-Linear Models -- Decision Tree Explanation -- Data Preparation for the Decision Tree Model -- Creating the Model -- Decision Tree - SHAP -- Partial Dependency Plot -- PDP Using Scikit-Learn -- Non-Linear Model Explanation - LIME -- Non-Linear Explanation - Skope-Rules -- Conclusion -- Chapter 5: Explainability for Ensemble Models -- Ensemble Models -- Types of Ensemble Models -- Why Ensemble Models? -- Using SHAP for Ensemble Models -- Using the Interpret Explaining Boosting Model -- Ensemble Classification Model: SHAP -- Using SHAP to Explain Categorical Boosting Models |
| Title | Practical Explainable AI Using Python - Artificial Intelligence Model Explanations Using Python-Based Libraries, Extensions, and Frameworks |
| URI | https://app.knovel.com/hotlink/toc/id:kpPEAIUPA2/practical-explainable/practical-explainable?kpromoter=Summon https://cir.nii.ac.jp/crid/1130853708031233289 https://www.perlego.com/book/4513902/practical-explainable-ai-using-python-artificial-intelligence-model-explanations-using-pythonbased-libraries-extensions-and-frameworks-pdf https://ebookcentral.proquest.com/lib/[SITE_ID]/detail.action?docID=6838569 https://learning.oreilly.com/library/view/~/9781484271582/?ar http://link.springer.com/10.1007/978-1-4842-7158-2 https://www.vlebooks.com/vleweb/product/openreader?id=none&isbn=9781484271582 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwvV1Lb9NAEF71cYBcyqOIUBKtEAcOdWOPX2suKI0SNQhQDi2quKx27XWJbJwodqOWv4DEb2Z2bZO0IHHjYinx7vj17czsPAl5nfi2ZHEoLE9qa5UXAS4pCC3d6AUlklYxTLTFp-Dswnt_6V_ukG9tLoxubpUVi7XKDZv-uqi0I3NQLeLBPHmbLWfj4fRiNoRBk0QkckvdLPMm0-jv_77Llia0DaFRm5Z2yb6j5Zr24VobkwyEoJtgmvQv5kHo-CG0VaGa337rGG1q0-L-C89YeArx1iEdUWbIm5BvVSWKtPpBUGoV8znq10u1ytXV4q4uW4oUN8Ud8qDM5nleIu_9wydrRN3kgPxsX1Id4ZKdXFfyJP5-r37kf3uLj8i-0gkZj8mOKp6Qg7YNBW240lPyY9YSouMNITqcUhMPQWe3uj4CtehwZQKjcMXR6VYlUqr7wTVza9toeWemdYqSPqEfWsPCMQ41cf848JiKIqGTNsKtPCSfJ-Pz0ZnV9JiwBHio_VmQhiBshyVhwpRKbV-wwI4TF2SQ6sRmEUsVpJFyfUfZbiyDJE0lAxlGqYI09t1nZK9YFOo5oSGqVwAC4a0AZb5kdpCATETEHOVFadQlr7bwwde58YeXfAtgDLqkX385vqzLjXA9iG--WZf0EE48nuujgyoIKlx4ZWTO4Lq4fe6SwwZovCbv-ajl2ziPtrDj5sJN9C8fn44C5jI_wKm9Go7NzDXcvzf6G6X1EPBuQi6z0qTks8B3u-RNC96GSFsXGylxh2taXBPj8OJfT3pEHoJONjEGr5dkr1pdqx6qgJXsk93Rxy99s3z18dz7BWYVWsk |
| linkProvider | Knovel |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.title=Practical+explainable+AI+using+Python+%3A+artificial+intelligence+model+explanations+using+Python-based+libraries%2C+extensions%2C+and+frameworks&rft.au=Mishra%2C+Pradeepta&rft.date=2022-01-01&rft.pub=Apress&rft.isbn=9781484271575&rft_id=info:doi/10.1007%2F978-1-4842-7158-2&rft.externalDocID=BC11155459 |
| thumbnail_l | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fwww.perlego.com%2Fbooks%2FRM_Books%2Fingram_csplus_gexhsuob%2F9781484271582.jpg |
| thumbnail_m | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fwww.safaribooksonline.com%2Flibrary%2Fcover%2F9781484271582 http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fvle.dmmserver.com%2Fmedia%2F640%2F97814842%2F9781484271582.jpg |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcontent.knovel.com%2Fcontent%2FThumbs%2Fthumb14866.gif http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fmedia.springernature.com%2Fw306%2Fspringer-static%2Fcover-hires%2Fbook%2F978-1-4842-7158-2 |