Exam DP-100 topic 3 question 162 discussion

1. Load and configure the Responsible AI Insights dashboard constructor component. 2. Add the counterfactuals component to the Responsible AI Insights dashboard. 3. Use the Gather Responsible AI Insights dashboard component to present the dashboard. The RAI Insights dashboard constructor and Gather RAI Insights dashboard components are always required, plus at least one of the tool components. Ref : https://learn.microsoft.com/en-us/azure/machine-learning/how-to-responsible-ai-insights-sdk-cli?view=azureml-api-2&tabs=yaml#responsible-ai-components >> You must identify the features to modify for a differing model prediction result. Counterfactual component : to observe how feature perturbations would affect your model predictions while providing the closest data points with opposing or 'different model' predictions. Ref : https://learn.microsoft.com/en-us/azure/machine-learning/concept-responsible-ai-dashboard?view=azureml-api-2#responsible-ai-dashboard-components

seems correct. https://techcommunity.microsoft.com/t5/ai-machine-learning-blog/how-to-create-a-responsible-ai-dashboard-to-debug-ai-models-part/ba-p/3766710 https://techcommunity.microsoft.com/t5/ai-machine-learning-blog/how-to-generate-counterfactuals-for-a-model-with-responsible-ai/ba-p/3803934

The core components for constructing the Responsible AI dashboard in Azure Machine Learning are: RAI Insights dashboard constructor The tool components: Add Explanation to RAI Insights dashboard Add Causal to RAI Insights dashboard Add Counterfactuals to RAI Insights dashboard Add Error Analysis to RAI Insights dashboard Gather RAI Insights dashboard Gather RAI Insights score card The RAI Insights dashboard constructor and Gather RAI Insights dashboard components are always required, plus at least one of the tool components. However, it isn't necessary to use all the tools in every Responsible AI dashboard.