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
Explainable Deep Learning Models for Healthcare · LearnSpace
Назад в каталог
courseraАнализ данных

Explainable Deep Learning Models for Healthcare

Курс от University of Glasgow
Средний≈ 30.3 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course will introduce the concepts of interpretability and explainability in machine learning applications. The learner will understand the difference between global, local, model-agnostic and model-specific explanations. State-of-the-art explainability methods such as Permutation Feature Importance (PFI), Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanation (SHAP) are explained and applied in time-series classification. Subsequently, model-specific explanations such as Class-Activation Mapping (CAM) and Gradient-Weighted CAM are explained and implemented. The learners will understand axiomatic attributions and why they are important. Finally, attention mechanisms are going to be incorporated after Recurrent Layers and the attention weights will be visualised to produce local explanations of the model.

Навыки, которые вы освоите

Machine LearningDeep LearningArtificial Neural NetworksSoftware VisualizationRecurrent Neural Networks (RNNs)Responsible AIModel EvaluationPredictive ModelingApplied Machine LearningConvolutional Neural NetworksAutoencoders

Программа курса

4 модулей · 76 учебных материалов

01Interpretable vs Explainable Machine Learning Models in Healthcare22 материалов

Welcome

Welcome video - Explainable Deep Learning Models for HealthcareВидеоStay connected with UofG OnlineЧтение

Explanability in Machine Learning Models for Healthcare

Interpretability vs ExplainabilityВидео'Explainability' in Healthcare ApplicationsВидео

Учитесь у экспертов

Fani Deligianni

Dr

Explainable Deep Learning Models for Healthcare
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

≈ 30.3 ч

4 модулей

Язык: Английский

Субтитры: Арабский, Французский, Узбекский, Украинский, Китайский (Китай), Греческий, Итальянский, Бразильский португальский, Вьетнамский, Нидерландский, Корейский, Немецкий, Пушту, Русский, Тайский, Индонезийский, Шведский, Турецкий, Азербайджанский, Испанский, Хинди, Японский, Казахский, Венгерский, Польский

Часть программы вашего университета
The importance of explainable prediction models in healthcareЧтение

Taxonomy of Explainability Methods

Taxonomy of Explainability MethodsВидеоExplainable Artificial Intelligence - TaxonomyЧтениеModel Agnostic Explainability MethodsВидеоModel Agnostic ExplainabilityЧтение

Permutation Feature Importance in ECG Classification

Permutation Feature Importance in Time Series DataВидеоPermutation Feature ImportanceЧтениеPractical Exercise: Interpretability of the MLP model using Permutation Feature ImportanceЧтениеPractical Exercise: Interpretability of the CNN model using Permutation Feature ImportanceЧтениеPractical Exercise: Interpretability of the LSTM model using Permutation Feature ImportanceЧтениеExplainability models in ECGЧтение

End of Week 1

End of week 1 quizЗаданиеWeek 1 - Your experienceОбсуждение

Week 1 - Interactive notebook examples

Permutation feature importance for classifying heart beats using a CNNЛабораторнаяLight - Permutation feature importance for classifying heart beats using a CNNЛабораторнаяPermutation feature importance for classifying heart beats using an LSTMЛабораторнаяLight - Permutation feature importance for classifying heart beats using an LSTMЛабораторнаяPermutation feature importance for classifying heart beats using a multi-layer perceptronЛабораторная
02Local Explainability Methods for Deep Learning Models21 материалов

Local Interpretable Model Agnostic Explanations

Local Interpretable Model Agnostic Explanations (LIME)ВидеоLIME in Time-Series ClassificationВидеоWhy Should I Trust You?ЧтениеPractical Exercise: Interpretability of heartbeat classification using LIME and an NNMLP modelЧтениеPractical Exercise: Interpretability of heartbeat classification using LIME and a CNN modelЧтениеPractical Exercise: Interpretability of heartbeat classification using LIME and an LSTM modelЧтение

Shapley Additive Explanations

Shapley Additive ExplanationsВидеоA Unified Approach to Interpreting Model PredictionsЧтение

Model-Specific Explanations for Deep Learning: Visualisation Methods

Model-Specific Explanations: Visualisation MethodsВидеоCAM in Time-Series ClassificationВидеоPractical Exercise: Interpretability of CNN models using Class Activation MapsЧтениеClass Activation MappingЧтение

End of Week 2

End of week 2 quizЗаданиеWeek 2 - Your experienceОбсуждение

Week 2 - Interactive notebook examples

Interpretability of heartbeat classification using a CNN model and Class Activation MapsЛабораторнаяInterpretability of heartbeat classification using a CNN model and CAMЛабораторнаяLIME interpretability for heartbeat classification with a convolutional neural networkЛабораторнаяInterpretability of heartbeat classification using an LSTM model and CAMЛабораторнаяLIME interpretability for heartbeat classification with a long short-term memory networkЛабораторнаяLight - LIME interpretability for heartbeat classification with a long short-term memory networkЛабораторная
03Gradient-weighted Class Activation Mapping and Integrated Gradients19 материалов

Gradient Weighted Class Activation Maps

Gradient Weighted Class Activation MapsВидеоGRAD - Class Activation Mapping ЧтениеGrad-CAM in Time-Series ClassificationВидеоPractical Exercise: Interpretability of the CNN model using Gradient-weighted Class Activation MappingЧтениеPractical Exercise: Interpretability of the LSTM model using Gradient-weighted Class Activation MappingЧтение

Axiomatic Attributions and Integrated Gradients

Integrated GradientsВидеоAxiomatic Attribution for Deep NetworksЧтениеIntegrated Gradients in Time Series ClassificationВидеоPractical Exercise: Interpretability of the CNN model using Integrated GradientsЧтениеPractical Exercise: Interpretability of the LSTM model using Integrated GradientsЧтение

End of Week 3

End of week 3 quizЗаданиеWeek 3 - Your experienceОбсуждение

Week 3 - Interactive notebook examples

Interpretability of heartbeat classification using a CNN model and Grad-CAMЛабораторнаяInterpretability of heartbeat classification using integrated gradients and a CNN modelЛабораторнаяLight - Interpretability of heartbeat classification using integrated gradients and a CNN modelЛабораторнаяInterpretability of heartbeat classification using an LSTM model and Grad-CAMЛабораторнаяLight - Interpretability of heartbeat classification using an LSTM model and Grad-CAMЛабораторнаяInterpretability of heartbeat classification using integrated gradients and an LSTM modelЛабораторная
04Attention mechanisms in Deep Learning14 материалов

Week 4: Attention in RNN and Autoencoders

Attention in Deep LearningВидеоTaxonomy of AttentionВидеоSurvey on Attention MechanismsЧтениеAttention and ExplainabilityВидеоPractical Exercise: Classification of heartbeats using an LSTM with attention mechanismЧтениеPractical Exercise: Interpretability of the LSTM model with attention mechanismЧтение

End of Week 4

End of week 4 quizЗаданиеWeek 4 - Your experienceОбсуждение

Week 4 - Interactive notebook examples

Interpretability of heartbeat classification using an LSTM model with attention mechanismЛабораторнаяLight - Interpretability of heartbeat classification using an LSTM model with attention mechanismЛабораторнаяHeartbeat classification using an LSTM model with attention mechanismЛабораторнаяLight - Heartbeat classification using an LSTM model with attention mechanismЛабораторная

Explainable deep learning models for healthcare

End of course summative quizЗаданиеKeeping Learning with UofG OnlineЧтение
LIME interpretability for heartbeat classification with a multi-layer perceptronЛабораторная
Light - Interpretability of heartbeat classification using integrated gradients and an LSTM modelЛабораторная