Wrap-up
Closing and useful resources.
Last updated
Closing and useful resources.
Last updated
In this lab, we walked through the use of Watson OpenScale’s performance monitoring, bias mitigation and explainability features. Showing how these capabilities help to provide insight into model performance at runtime and can ultimately create more fair and explainable outcomes for customers.
Below are some additional tips, resources and links you can explore.
If you used a Spark Python Jupyter kernel to run the lab, you can stop the environments to save capacity unit hours on your account
In the Watson Studio web interface. Click on the three horizontal bars on the top left corner.
From the menu, expand the 'Manage section and select the 'Environment Runtimes' option.
Under the 'Active environment runtimes', if you see any running environments, you can shut them down by clicking on the three vertical dots under the 'Actions' column and selected the 'Stop' option
Trust in AI from IBM Research
and . These free toolkits allow data scientists to identify potential issues with their models at build time.
