Welcome video - Explainable Deep Learning Models for Healthcare - Interpretable vs Explainable Machine Learning Models in Healthcare | Coursera

Welcome video - Explainable Deep Learning Models for Healthcare

video-placeholder

Loading...

University of Glasgow

Explainable deep learning models for healthcare - CDSS 3

University of Glasgow

Course 3 of 5 in the Informed Clinical Decision Making using Deep Learning Specialization

Enroll for Free

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.

Skills You'll Learn

attention mechanisms, explainable machine learning models, model-agnostic and model specific models, global and local explanations, interpretability vs explainability

From the lesson

Interpretable vs Explainable Machine Learning Models in Healthcare

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.

Welcome video - Explainable Deep Learning Models for Healthcare0:55

Taught By

Fani Deligianni
Dr

Try the Course for Free

Explore our Catalog

Join for free and get personalized recommendations, updates and offers.