К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Explainability Methods & Evaluation · LearnSpace
Назад в каталог
courseraАнализ данных

Explainability Methods & Evaluation

Курс от Edureka
Средний≈ 8.3 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course explores advanced Explainable AI (XAI) techniques for interpreting and validating machine learning model behavior. It focuses on methods that move beyond simple feature importance toward mathematically grounded insights into black-box models. Through structured lessons and practical demonstrations, you will learn how Shapley theory underpins fair feature attribution, how SHAP methods generate local and global explanations, and how surrogate and rule-based approaches approximate model behavior. You will also work with counterfactual and contrastive explanations, including how to generate actionable alternatives and evaluate plausibility under perturbations and adversarial conditions. The course progresses from mathematical foundations to applied evaluation, emphasizing fidelity, faithfulness, stability, and reliability. Rather than treating explanations as visual outputs, it focuses on critically analyzing whether they accurately reflect model behavior. By the end of this course, you will be able to: - Explain the mathematical foundations of Shapley values and fair feature attribution - Apply SHAP techniques such as TreeSHAP, KernelSHAP, and interaction values - Design and evaluate surrogate and rule-based explanation methods - Generate and assess counterfactuals using practical evaluation metrics - Measure explanation quality through fidelity, faithfulness, stability, robustness, and sparsity - Test explanation reliability under perturbations and adversarial manipulation This course is ideal for machine learning engineers, AI researchers, data scientists, and professionals building trustworthy AI systems. A foundational understanding of ML concepts and Python-based model development is recommended; prior experience with explainability techniques is not required. Join us to learn how to design and validate XAI systems that deliver transparent, reliable insights into machine learning models.

Навыки, которые вы освоите

Model EvaluationFeature EngineeringModel TrainingAI SecurityData ScienceStatistical MethodsResponsible AIPython ProgrammingData ManagementMachine Learning AlgorithmsData AnalysisApplied Machine LearningTestabilityPredictive ModelingPredictive AnalyticsModel OptimizationData PreprocessingData Visualization

Программа курса

4 модулей · 63 учебных материалов

01Feature Attribution and Interpretable Modeling20 материалов

Shapley Theory

Course IntroductionВидеоCourse SyllabusЧтениеCooperative Game TheoryВидеоShapley ValuesВидео

Учитесь у экспертов

Edureka

Преподаватель курса

Explainability Methods & Evaluation
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 8.3 ч

4 модулей

Язык: Английский

Часть программы вашего университета
Hands-On: Manual Shapley Value CalculationВидео
Why Fair Attribution Matters: Interpreting Feature Contributions in Real-World ModelsЧтение
Knowledge Check: Shapley TheoryЗадание

SHAP Methods for Model Explanation

TreeSHAP and KernelSHAPВидеоHands-On: Comparing SHAP VariantsВидеоHands-On: SHAP Interaction ValuesВидеоScalability and Performance Challenges in SHAP-Based ExplanationsЧтениеKnowledge Check: SHAP Methods for Model ExplanationЗадание

Surrogate and Rule-Based Explanations

Global Surrogate Models and FidelityВидеоRule Extraction from Black-Box ModelsВидеоHands-On: Training and Evaluating a Surrogate ModelВидеоLimitations and Failure Modes of Explanation MethodsЧтениеKnowledge Check: Surrogate and Rule-Based ExplanationsЗадание

Module Wrap-Up and Assessment

Reflecting on Feature Attribution and Model InterpretabilityDIALOGUEModule Summary: Feature Attribution and Interpretable ModelingЧтениеKnowledge Check: Feature Attribution and Interpretable ModelingЗадание
02Counterfactual and Contrastive Methods18 материалов

Foundations of Counterfactual Explanations

Counterfactual ExplanationsВидеоActionability and Feasibility ConstraintsВидеоHands-On: Generating Counterfactual ExplanationsВидеоDiversity in Counterfactual ExplanationsЧтениеKnowledge Check: Foundations of Counterfactual ExplanationsЗадание

Metrics for Counterfactual Explanations

Evaluation Metrics for CounterfactualsВидеоRobustness of Counterfactual ExplanationsВидеоHands-On: Validating and Comparing Counterfactual MethodsВидеоHands-On: Applying Evaluation Metrics to CounterfactualsВидеоBenchmarking Counterfactual Explanation MethodsЧтениеKnowledge Check: Metrics for Counterfactual ExplanationsЗадание

Contrastive Explanations

Contrastive Reasoning for Model ExplanationsВидеоHands-On: Implementing Contrastive ExplanationsВидеоSelecting Meaningful Foils in Contrastive ExplanationsЧтениеKnowledge Check: Contrastive ExplanationsЗадание

Module Wrap-Up and Assessment

Analyzing Model Decisions Through Counterfactual and Contrastive ThinkingDIALOGUEModule Summary: Counterfactual and Contrastive MethodsЧтениеKnowledge Check: Counterfactual and Contrastive MethodsЗадание
03Evaluating Explanation Methods20 материалов

Evaluation Criteria for Explanations

Fidelity, Faithfulness and Stability in ExplanationsВидеоQuantitative Metrics for Attribution EvaluationВидеоHands-On: Faithfulness Testing Using Feature RemovalВидеоQualitative Evaluation of Explanation MethodsЧтениеKnowledge Check: Evaluation Criteria for ExplanationsЗадание

Robustness of Explanations

Sensitivity of Attribution Methods to Input PerturbationsВидеоAdversarial Manipulation of ExplanationsВидеоHands-On: Robustness Testing of SHAP and LIMEВидеоHands-On: LIME Robustness Evaluation and Comparative AnalysisВидеоModel Dependence of Explanation MethodsЧтениеKnowledge Check: Robustness of ExplanationsЗадание

Human Evaluation of Explanations

Human Interpretability and Mathematical FaithfulnessВидеоDesigning Comparative Studies for Explanation MethodsВидеоMini Project: Comparative Evaluation of XAI TechniquesВидеоMini Project: Completing the Evaluation of XAI TechniquesВидеоCognitive Biases in Interpreting AI ExplanationsЧтениеHuman Evaluation of ExplanationsЗадание

Module Wrap-Up and Assessment

Assessing Explanation Quality: Fidelity, Robustness, and Human FactorsDIALOGUEModule Summary: Evaluating Explanation MethodsЧтениеKnowledge Check: Evaluating Explanation MethodsЗадание
04Course Wrap-Up and Assessments5 материалов

Course Conclusion

Practice Project: Designing and Evaluating an Explainable AI Framework for FinTrust AnalyticsЧтениеGuiding Interpretation of Model ExplanationsDIALOGUEEnd Course Knowledge Check: Explainability & EvaluationЗаданиеDesigning Robust and Interpretable Explainable AI SystemsЗаданиеCourse SummaryВидео