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.
Schenken Sie Ihrer Karriere Coursera Plus mit einem Rabatt von $160 , der jährlich abgerechnet wird. Sparen Sie heute.
Explainable deep learning models for healthcare - CDSS 3
Dieser Kurs ist Teil von Spezialisierung Informed Clinical Decision Making using Deep Learning
Dozent: Fani Deligianni
1.641 bereits angemeldet
Bei 
enthalten
(15 Bewertungen)
Empfohlene Erfahrung
Was Sie lernen werden
Program global explainability methods in time-series classification
Program local explainability methods for deep learning such as CAM and GRAD-CAM
Understand axiomatic attributions for deep learning networks
Incorporate attention in Recurrent Neural Networks and visualise the attention weights
Kompetenzen, die Sie erwerben
- Kategorie: global and local explanations
- Kategorie: explainable machine learning models
- Kategorie: attention mechanisms
- Kategorie: interpretability vs explainability
- Kategorie: model-agnostic and model specific models
Wichtige Details
Zu Ihrem LinkedIn-Profil hinzufügen
5 Aufgaben
Erfahren Sie, wie Mitarbeiter führender Unternehmen gefragte Kompetenzen erwerben.
Erweitern Sie Ihre Fachkenntnisse
- Lernen Sie neue Konzepte von Branchenexperten
- Gewinnen Sie ein Grundverständnis bestimmter Themen oder Tools
- Erwerben Sie berufsrelevante Kompetenzen durch praktische Projekte
- Erwerben Sie ein Berufszertifikat zur Vorlage
Erwerben Sie ein Karrierezertifikat.
Fügen Sie diese Qualifikation zur Ihrem LinkedIn-Profil oder Ihrem Lebenslauf hinzu.
Teilen Sie es in den sozialen Medien und in Ihrer Leistungsbeurteilung.
In diesem Kurs gibt es 4 Module
Deep learning models are complex and it is difficult to understand their decisions. Explainability methods aim to shed light to the deep learning decisions and enhance trust, avoid mistakes and ensure ethical use of AI. Explanations can be categorised as global, local, model-agnostic and model-specific. Permutation feature importance is a global, model agnostic explainabillity method that provide information with relation to which input variables are more related to the output.
Das ist alles enthalten
6 Videos8 Lektüren1 Aufgabe1 Diskussionsthema5 Unbewertete Labore
Local explainability methods provide explanations on how the model reach a specific decision. LIME approximates the model locally with a simpler, interpretable model. SHAP expands on this and it is also designed to address multi-collinearity of the input features. Both LIME and SHAP are local, model-agnostic explanations. On the other hand, CAM is a class-discriminative visualisation techniques, specifically designed to provide local explanations in deep neural networks.
Das ist alles enthalten
5 Videos7 Lektüren1 Aufgabe1 Diskussionsthema7 Unbewertete Labore
GRAD-CAM is an extension of CAM, which aims to a broader application of the architecture in deep neural networks. Although, it is one of the most popular methods in explaining deep neural network decisions, it violates key axiomatic properties, such as sensitivity and completeness. Integrated gradients is an axiomatic attribution method that aims to cover this gap.
Das ist alles enthalten
4 Videos6 Lektüren1 Aufgabe1 Diskussionsthema7 Unbewertete Labore
Attention in deep neural networks mimics human attention that allocates computational resources to a small range of sensory input in order to process specific information with limited processing power. In this week, we discuss how to incorporate attention in Recurrent Neural Networks and autoencoders. Furthermore, we visualise attention weights in order to provide a form of inherent explanation for the decision making process.
Das ist alles enthalten
3 Videos3 Lektüren2 Aufgaben1 Diskussionsthema4 Unbewertete Labore
Dozent
Empfohlen, wenn Sie sich für Machine Learning interessieren
Duke University
University of Illinois Urbana-Champaign
University of Illinois Urbana-Champaign
University of Glasgow
Warum entscheiden sich Menschen für Coursera für ihre Karriere?
Neue Karrieremöglichkeiten mit Coursera Plus
Unbegrenzter Zugang zu über 7.000 erstklassigen Kursen, praktischen Projekten und Zertifikatsprogrammen, die Sie auf den Beruf vorbereiten – alles in Ihrem Abonnement enthalten
Bringen Sie Ihre Karriere mit einem Online-Abschluss voran.
Erwerben Sie einen Abschluss von erstklassigen Universitäten – 100 % online
Schließen Sie sich mehr als 3.400 Unternehmen in aller Welt an, die sich für Coursera for Business entschieden haben.
Schulen Sie Ihre Mitarbeiter*innen, um sich in der digitalen Wirtschaft zu behaupten.
Häufig gestellte Fragen
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
If you subscribed, you get a 7-day free trial during which you can cancel at no penalty. After that, we don’t give refunds, but you can cancel your subscription at any time. See our full refund policy.