This module covers a special topic related to explaining and trusting predictions in ML systems.
You can find the slides for the guest lecture in this module at Explaining and Trusting Predictions.
- The challenges of trusting predictions and the model quality
- Desired characteristics for explainers
- Introducing an approach for explaining predictions and the model
- Ribeiro M. T., Singh S., Guestrin C., Why should I trust you? Explaininf the Predictions on Any Classifier.. KDD 2016.