Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Birmingham ; Mumbai
Packt
July 2020
|
| Schriftenreihe: | Expert insight
|
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV046931531 | ||
| 003 | DE-604 | ||
| 005 | 20231128 | ||
| 007 | t| | ||
| 008 | 201008s2020 xx a||| |||| 00||| eng d | ||
| 020 | |a 9781800208131 |c Pb.: £ 37.99 |9 978-1-80020-813-1 | ||
| 035 | |a (OCoLC)1224011962 | ||
| 035 | |a (DE-599)BVBBV046931531 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-706 |a DE-19 |a DE-473 |a DE-1043 | ||
| 084 | |a ST 250 |0 (DE-625)143626: |2 rvk | ||
| 084 | |a ST 250 |0 (DE-625)143626: |2 rvk | ||
| 100 | 1 | |a Rothman, Denis |e Verfasser |0 (DE-588)1221752987 |4 aut | |
| 245 | 1 | 0 | |a Hands-on Explainable AI (XAI) with Python |b interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps |c Denis Rothmann |
| 264 | 1 | |a Birmingham ; Mumbai |b Packt |c July 2020 | |
| 300 | |a xviii, 428 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 0 | |a Expert insight | |
| 650 | 0 | 7 | |a Python |g Programmiersprache |0 (DE-588)4434275-5 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |D s |
| 689 | 0 | 1 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | 2 | |a Python |g Programmiersprache |0 (DE-588)4434275-5 |D s |
| 689 | 0 | |5 DE-604 | |
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |z 978-1-80020-276-4 |
| 856 | 4 | 2 | |m Digitalisierung UB Bamberg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032340451&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-032340451 | |
Datensatz im Suchindex
| DE-19_call_number | 1505/ST 250 R845 |
|---|---|
| DE-19_location | 80 |
| DE-473_call_number | 656/ST 250p99 GA 13199 |
| DE-473_location | 7 |
| DE-BY-UBG_katkey | 196872489 |
| DE-BY-UBG_media_number | 013908615364 |
| DE-BY-UBM_katkey | 6194035 |
| DE-BY-UBM_media_number | 41632169910018 |
| _version_ | 1824053877122531328 |
| adam_text | Tableof Contents Preface______________________ xj Chapter 1: Explaining Artificial Intelligence with Python____________ 1 Defining explainable Al 3 Going from black box models to XAI white box models 4 Explaining and interpreting 6 Designing and extracting 6 The XAI executive function 7 The XAI medical diagnosis timeline 10 The standard Al program used by a general practitioner 11 Definition of a KNN algorithm A KNN in Python 11 12 West Nile virus - a case of life or death 19 How can a lethal mosquito bite go unnoticed? What is the West Nile virus? How did the West Nile virus get to Chicago? 20 22 23 XAI can save lives using Google Location History Downloading Google Location History Google’s Location History extraction tool Reading and displaying Google Location History data Installation of the basemap packages The import instructions Importing the data Processing the data for XAI and basemap Setting up the plotting options to display the map Enhancing the Al diagnosis with XAI Enhanced KNN 26 26 28 31 33 33 34 35 36 41 41 XAI applied to the medical diagnosis experimental program 45 Displaying the KNN plot Natural language explanations Displaying the Location History map Showing mosquito detection data and natural language explanations A critical diagnosis is reached with XAI 46 47 48 49 50 Summary Questions 50 51 --------------------------------------------------------------- [i]--------------- —---------------------------------------------
Table of Contents_______________________________________________ ___________________________________________ _________________________________ —-------------------------------------- References Further reading Chapter 2: White Box XAI for Al Bias and Ethics_______________ Moral Al bias in self-driving cars Life and death autopilot decision making The trolley problem The MIT Moral Machine experiment Real life and death situations Explaining the moral limits of ethical Al Standard explanation of autopilot decision trees The SDC autopilot dilemma Importing the modules Retrieving the dataset Reading and splitting the data Theoretical description of decision tree classifiers Creating the default decision tree classifier Training, measuring, and saving the model Displaying a decision tree XAI applied to an autopilot decision tree Structure of a decision tree The default output of the default structure of a decision tree The customized output of a customized structure of a decision tree The output of a customized structure of a decision tree Using XAI and ethics to control a decision tree Loading the model Accuracy measurements Simulating real-time cases Introducing ML bias due to noise Introducing ML ethics and laws Case 1 - not overriding traffic regulations to save four pedestrians Case 2 - overriding traffic regulations Case 3 - introducing emotional intelligence in the autopilot Summary Questions References Further reading ®2 52 53 55 55 55 57 58 59 61 61 62 63 64 66 68 69 71 74 74 74 76 78 81 82 82 83 83 85 85 87 87 gg gg go go
Table of Contents Chapter 3: Explaining Machine Learning with Facets______________ 91 Getting started with Facets Ց2 Installing Facets on Google Colaboratory 93 Retrieving the datasets 93 Reading the data files 94 Facets Overview 95 Creating feature statistics for the datasets 95 Implementing the feature statistics code Implementing the HTML code to display feature statistics Sorting the Facets statistics overview Sorting data by feature order XAI motivation for sorting features Sorting by non-uniformity Sorting by alphabetical order Sorting by amount missing/zero Sorting by distribution distance Facets Dive Building the Facets Dive display code Defining the labels of the data points Defining the color of the data points Defining the binning of the x axis and y axis Defining the scatter plot of the x axis and the y axis Summary Questions References Further reading Chapter 4: Microsoft Azure Machine Learning Model Interpretability with SHAP________________________________ Introduction to SHAP Key SHAP principles Symmetry Null player Additivity A mathematical expression of the Shapley value Sentiment analysis example Shapley value for the first feature, good Shapley value for the second feature, excellent Verifying the Shapley values Getting started with SHAP Installing SHAP Importing the modules Importing the data 95 96 97 98 98 99 102 103 103 105 105 107 109 110 111 113 114 114 114 115 117 117 117 118 119 120 122 124 1 շ6 1շ7 128 128 1շ8 1շ9
Table of Contents________________________________________ _____________________________ —---------------------------------------------------------------- 130 Intercepting the dataset Vectorizing the datasets Linear models and logistic regression Creating, training, and visualizing the output of a linear model Defining a linear model Agnostic model explaining with SHAP Creating the linear model explainer Creating the plot function Explaining the output of the model s prediction Explaining intercepted dataset reviews with SHAP Explaining the original IMDb reviews with SHAP Summary Questions References Further reading Additional publications Chapter 5: Building an Explainable Al Solution from Scratch Moral, ethical, and legal perspectives The U.S. census data problem Using pandas to display the data Moral and ethical perspectives The moral perspective The ethical perspective The legal perspective 136 138 138 141 143 143 143 145 147 150 155 156 156 157 157 159 160 161 162 165 165 167 168 The machine learning perspective Displaying the training data with Facets Dive Analyzing the training data with Facets Verifying the anticipated outputs Using KMC to verify the anticipated results Analyzing the output of the KMC algorithm Conclusion of the analysis 170 170 173 177 177 180 183 Transforming the input data 184 WIT applied to a transformed dataset 186 Summary 195 Questions ig6 References igg Further reading ig6 Chapter 6: AI Fairness with Google s What-lf Tool (WIT)___________197 Interpretability and explainability from an ethical Al perspective 198 The ethical perspective 1 gg The
legal perspective 200 Explaining and interpreting 200 [iv]
Table of Contents Preparing an ethical dataset Getting started with WIT Importing the dataset Preprocessing the data Creating data structures to train and test the model Creating a DNN model Training the model Creating a SHAP explainer The plot of Shapley values Model outputs and SHAP values The WIT datapoint explorer and editor Creating WIT The datapoint editor Features Performance and fairness Ground truth Cost ratio Slicing Fairness The ROC curve and AUC The PR curve The confusion matrix 201 204 205 206 208 208 211 211 21 շ 212 216 216 218 221 222 222 223 224 224 225 228 229 Summary 229 Questions 230 References 231 Further reading 231 Chapter 7: A Python Client for Explainable Al Chatbots___________233 The Python client for Dialogflow 234 Installing the Python client for Google Dialogflow 235 Creating a Google Dialogflow agent 236 Enabling APIs and sen/ices 239 The Google Dialogflow Python client 241 Enhancing the Google Dialogflow Python client 245 Creating a dialog function 245 The constraints of an XAI implementation on Dialogflow 246 Creating an intent in Dialogflow 247 The training phrases of the intent The response of an intent Defining a follow-up intent for an 248 24® intent 249 The XAI Python client 254 Inserting interactions in the MDP 255 Interacting with Dialogflow with the Python client A CUI XAI dialog using Google Dialogflow -------------------------------------------------------------------------------------------- [V] 259 259 ---------- ------------------ --- -------------------------------------------------------------
Table of Contents ________________________________ __________________ Dialogflow integration for a website A Jupyter Notebook XAI agent manager Google Assistant Summary Questions Further reading Chapter 8: Local Interpretable Model-Agnostic Explanations (LIME) _____________________________ Introducing LIME A mathematical representation of LIME Getting started with LIME Installing LIME on Google Colaboratory Retrieving the datasets and vectorizing the dataset An experimental AutoML module Creating an agnostic AutoML template Bagging classifiers Gradient boosting classifiers Decision tree classifiers Extra trees classifiers Interpreting the scores Training the model and making predictions The interactive choice of classifier Finalizing the prediction process Interception functions 260 263 264 266 267 267 269 270 272 274 275 275 276 277 279 280 280 281 282 283 283 284 285 The LIME explainer Creating the LIME explainer Interpreting LIME explanations 286 288 290 Explaining the predictions as a list Explaining with a plot Conclusions of the LIME explanation process Summary Questions References Further reading Chapter 9: The Counterfactual Explanations Method The counterfactual explanations method Dataset and motivations Visualizing counterfactual distances in WIT Exploring data point distances with the default view The logic of counterfactual explanations Belief 290 292 295 295 296 297 297 299 301 301 302 304 310 310 [vi]
Table of Contents 312 314 Truth Justification Sensitivity 314 The choice of distance functions 316 The L1 norm 316 The L2 norm 319 Custom distance functions 320 The architecture of the deep learning model 320 Invoking WIT 321 The custom prediction function for WIT 322 Loading a Keras model 324 Retrieving the dataset and model 325 Summary 326 Questions 327 References 327 Further reading 327 Chapter 10: Contrastive XAI_____________________________________ 329 The contrastive explanations method 330 Getting started with the CEM applied to MNIST 333 Installing Alibi and importing the modules 333 Importing the modules and the dataset 333 Importing the modules Importing the dataset Preparing the data 333 334 335 Defining and training the CNN model Creating the CNN model Training the CNN model Loading and testing the accuracy of the model Defining and training the autoencoder Creating the autoencoder Training and saving the autoencoder Comparing the original images with the decoded images Pertinent negatives CEM parameters Initializing the CEM explainer Pertinent negative explanations Summary Questions References Further reading [vii] 337 339 340 341 342 343 344 345 347 348 349 350 352 353 353 353
Table of Contents ______________ _____ ______ —-------------------- -------------------- Chapter 11: Anchors XAI__________ ________________— Anchors Al explanations Predicting income Classifying newsgroup discussions Anchor explanations for ImageNet Installing Alibi and importing the modules Loading an lnceptionV3 model Downloading an image Processing the image and making predictions Building the anchor image explainer Explaining other categories Other images and difficulties Summary Questions References Further reading Chapter 12: Cognitive XAI__________________________ Cognitive rule-based explanations From XAI tools to XAI concepts Defining cognitive XAI explanations A cognitive XAI method Importing the modules and the data The dictionaries The global parameters The cognitive explanation function The marginal contribution of a feature A mathematical perspective The Python marginal cognitive contribution function A cognitive approach to vectorizers Explaining the vectorizer for LIME Explaining the IMDb vectorizer for SHAP Human cognitive input for the CEM Rule-based perspectives Summary Questions Further reading Answers to the Questions_________________________ Chapter 1, Explaining Artificial Intelligence with Python Chapter 2, White Box XAI for Al Bias and Ethics Chapter 3, Explaining Machine Learning with Facets Chapter 4, Microsoft Azure Machine Learning Model 355 357 357 359 361 361 362 363 364 364 367 369 371 372 373 373 375 377 377 378 380 380 381 382 383 386 386 387 390 391 393 396 397 401 402 403 405 405 406 407
Table of Contents Interpretability with SHAP Chapter 5, Building an Explainable Al Solution from Scratch Chapter 6, Al Fairness with Google s What-lf Tool (WIT) Chapter 7, A Python Client for Explainable Al Chatbots Chapter 8, Local Interpretable Model-Agnostic Explanations (LIME) Chapter 9, The Counterfactual Explanations Method Chapter 10, Contrastive XAI Chapter 11, Anchors XAI Chapter 12, Cognitive XAI Other Books You May Enjoy______________ 409 410 411 412 413 414 415 416 417 419 index______________ 423
|
| any_adam_object | 1 |
| author | Rothman, Denis |
| author_GND | (DE-588)1221752987 |
| author_facet | Rothman, Denis |
| author_role | aut |
| author_sort | Rothman, Denis |
| author_variant | d r dr |
| building | Verbundindex |
| bvnumber | BV046931531 |
| classification_rvk | ST 250 |
| ctrlnum | (OCoLC)1224011962 (DE-599)BVBBV046931531 |
| discipline | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01804nam a2200397 c 4500</leader><controlfield tag="001">BV046931531</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20231128 </controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">201008s2020 xx a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781800208131</subfield><subfield code="c">Pb.: £ 37.99</subfield><subfield code="9">978-1-80020-813-1</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1224011962</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV046931531</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-706</subfield><subfield code="a">DE-19</subfield><subfield code="a">DE-473</subfield><subfield code="a">DE-1043</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 250</subfield><subfield code="0">(DE-625)143626:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 250</subfield><subfield code="0">(DE-625)143626:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Rothman, Denis</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1221752987</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Hands-on Explainable AI (XAI) with Python</subfield><subfield code="b">interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps</subfield><subfield code="c">Denis Rothmann</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Birmingham ; Mumbai</subfield><subfield code="b">Packt</subfield><subfield code="c">July 2020</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xviii, 428 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="0" ind2=" "><subfield code="a">Expert insight</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Python</subfield><subfield code="g">Programmiersprache</subfield><subfield code="0">(DE-588)4434275-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Python</subfield><subfield code="g">Programmiersprache</subfield><subfield code="0">(DE-588)4434275-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="z">978-1-80020-276-4</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Bamberg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032340451&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-032340451</subfield></datafield></record></collection> |
| id | DE-604.BV046931531 |
| illustrated | Illustrated |
| indexdate | 2025-02-14T18:11:05Z |
| institution | BVB |
| isbn | 9781800208131 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-032340451 |
| oclc_num | 1224011962 |
| open_access_boolean | |
| owner | DE-706 DE-19 DE-BY-UBM DE-473 DE-BY-UBG DE-1043 |
| owner_facet | DE-706 DE-19 DE-BY-UBM DE-473 DE-BY-UBG DE-1043 |
| physical | xviii, 428 Seiten Illustrationen, Diagramme |
| publishDate | 2020 |
| publishDateSearch | 2020 |
| publishDateSort | 2020 |
| publisher | Packt |
| record_format | marc |
| series2 | Expert insight |
| spellingShingle | Rothman, Denis Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps Python Programmiersprache (DE-588)4434275-5 gnd Künstliche Intelligenz (DE-588)4033447-8 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)4434275-5 (DE-588)4033447-8 (DE-588)4193754-5 |
| title | Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps |
| title_auth | Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps |
| title_exact_search | Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps |
| title_full | Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps Denis Rothmann |
| title_fullStr | Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps Denis Rothmann |
| title_full_unstemmed | Hands-on Explainable AI (XAI) with Python interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps Denis Rothmann |
| title_short | Hands-on Explainable AI (XAI) with Python |
| title_sort | hands on explainable ai xai with python interpret visualize explain and integrate reliable ai for fair secure and trustworthy ai apps |
| title_sub | interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps |
| topic | Python Programmiersprache (DE-588)4434275-5 gnd Künstliche Intelligenz (DE-588)4033447-8 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Python Programmiersprache Künstliche Intelligenz Maschinelles Lernen |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032340451&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT rothmandenis handsonexplainableaixaiwithpythoninterpretvisualizeexplainandintegratereliableaiforfairsecureandtrustworthyaiapps |