You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/machine-learning/how-to-use-automated-ml-for-ml-models.md
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -265,23 +265,23 @@ To generate a Responsible AI dashboard for a particular model,
265
265
266
266
1. While submitting an Automated ML job, proceed to the **Task settings** section on the left nav bar and select the **View additional configuration settings** option.
267
267
268
-
1. In the new form appearing post that selection, select the **Explain best model** checkbox.
268
+
2. In the new form appearing post that selection, select the **Explain best model** checkbox.
269
269
270
270
271
271
272
272

273
273
274
-
1. Proceed to the **Compute** page of the setup form and choose the **Serverless** as your compute.
274
+
3. Proceed to the **Compute** page of the setup form and choose the **Serverless** as your compute.
1. Once complete, navigate to the Models page of your Automated ML job, which contains a list of your trained models. Select on the **View Responsible AI dashboard** link:
278
+
4. Once complete, navigate to the Models page of your Automated ML job, which contains a list of your trained models. Select on the **View Responsible AI dashboard** link:
279
279
280
-

280
+

281
281
282
282
The Responsible AI dashboard appears for that model as shown in this image:
283
283
284
-

284
+

285
285
286
286
In the dashboard, you'll find four components activated for your Automated ML’s best model:
287
287
@@ -292,7 +292,7 @@ In the dashboard, you'll find four components activated for your Automated ML’
292
292
|[Model Explanations](how-to-machine-learning-interpretability.md)| Use the model explanation component to generate human-understandable descriptions of the predictions of a machine learning model by looking at: <br> Global explanations: For example, what features affect the overall behavior of a loan allocation model? <br> Local explanations: For example, why was a customer's loan application approved or rejected? |[Model Explainability Charts](how-to-responsible-ai-dashboard.md#feature-importances-model-explanations)|
293
293
|[Data Analysis](concept-data-analysis.md)| Use data analysis when you need to: <br> Explore your dataset statistics by selecting different filters to slice your data into different dimensions (also known as cohorts). <br> Understand the distribution of your dataset across different cohorts and feature groups. <br> Determine whether your findings related to fairness, error analysis, and causality (derived from other dashboard components) are a result of your dataset's distribution. <br> Decide in which areas to collect more data to mitigate errors that come from representation issues, label noise, feature noise, label bias, and similar factors. |[Data Explorer Charts](how-to-responsible-ai-dashboard.md#data-analysis)|
294
294
295
-
1. You can further create cohorts (subgroups of data points that share specified characteristics) to focus your analysis of each component on different cohorts. The name of the cohort that's currently applied to the dashboard is always shown at the top left of your dashboard. The default view in your dashboard is your whole dataset, titled "All data" (by default). Learn more about the [global control of your dashboard here.](how-to-responsible-ai-dashboard.md#global-controls)
295
+
5. You can further create cohorts (subgroups of data points that share specified characteristics) to focus your analysis of each component on different cohorts. The name of the cohort that's currently applied to the dashboard is always shown at the top left of your dashboard. The default view in your dashboard is your whole dataset, titled "All data" (by default). Learn more about the [global control of your dashboard here.](how-to-responsible-ai-dashboard.md#global-controls)
0 commit comments