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.
Explainable deep learning models for healthcare - CDSS 3
Ce cours fait partie de Spécialisation Informed Clinical Decision Making using Deep Learning
Enseigné en Anglais
Instructeur : Fani Deligianni
1 593 déjà inscrits
Inclus avec 
Cours
(15 avis)
Expérience recommandée
Ce que vous apprendrez
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
Compétences que vous acquerrez
- Catégorie : global and local explanations
- Catégorie : explainable machine learning models
- Catégorie : attention mechanisms
- Catégorie : interpretability vs explainability
- Catégorie : model-agnostic and model specific models
Détails à connaître
Ajouter à votre profil LinkedIn
5 quizzes
Cours
(15 avis)
Expérience recommandée
Découvrez comment les employés des entreprises prestigieuses maîtrisent des compétences recherchées
Élaborez votre expertise du sujet
- Apprenez de nouveaux concepts auprès d'experts du secteur
- Acquérez une compréhension de base d'un sujet ou d'un outil
- Développez des compétences professionnelles avec des projets pratiques
- Obtenez un certificat professionnel partageable
Obtenez un certificat professionnel
Ajoutez cette qualification à votre profil LinkedIn ou à votre CV
Partagez-le sur les réseaux sociaux et dans votre évaluation de performance
Il y a 4 modules dans ce cours
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.
Inclus
6 vidéos8 lectures1 quiz1 sujet de discussion5 laboratoires non notés
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.
Inclus
5 vidéos7 lectures1 quiz1 sujet de discussion7 laboratoires non notés
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.
Inclus
4 vidéos6 lectures1 quiz1 sujet de discussion7 laboratoires non notés
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.
Inclus
3 vidéos3 lectures2 quizzes1 sujet de discussion4 laboratoires non notés
Instructeur
Offert par
Recommandé si vous êtes intéressé(e) par Machine Learning
Pour quelles raisons les étudiants sur Coursera nous choisissent-ils pour leur carrière ?
Ouvrez de nouvelles portes avec Coursera Plus
Accès illimité à plus de 7 000 cours de renommée internationale, à des projets pratiques et à des programmes de certificats reconnus sur le marché du travail, tous inclus dans votre abonnement
Faites progresser votre carrière avec un diplôme en ligne
Obtenez un diplôme auprès d’universités de renommée mondiale - 100 % en ligne
Rejoignez plus de 3 400 entreprises mondiales qui ont choisi Coursera pour les affaires
Améliorez les compétences de vos employés pour exceller dans l’économie numérique
Foire Aux Questions
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.