Keep Calm and Trust your Model - On Explainability of Machine Learning Models
summary
Covers research and methods for making machine learning models interpretable and explaining predictions for both deep learning and classical ML, with mathematical intuition for how those approaches work. Discusses and compares specific explainability techniques from recent literature and demonstrates practical usage with open-source Python tools during a live demo.
AI-written summary · about
chapters (5)
- 0:00Start
- 3:25What do our models learn?
- 5:02Tree Interpreter
- 14:09Model Agnostic approaches
- 15:08LIME (Locally Interpretable Model-agnostic Explanations)
related talks
46mExplaining a Machine Learning blackbox
24mWhy and How to Build Explainability into your ML Workflow
32mOn the Importance of Explainability
01h 29mNavigating ML Explainability: From Theory to Implementation
35mWhy Do You Need an Explainable Ai?
45mExplainable Machine Learning Explained
16mBuilding Trust through Explainable AI
29mTowards Explainable Machine Learning