C1000-173 Exam Dumps and Practice Questions

Knowledge Accelerators are a part of IBM Knowledge Catalog in IBM Cloud Pak for Data and provide predefined industry-specific business terms and relationships. These accelerators are not included by default with sample assets nor automatically deployed through the Cloud Pak for Data marketplace. Instead, they are imported using dedicated API endpoints provided by IBM for Knowledge Accelerators. Deployment involves uploading the accelerator assets using the IBM Knowledge Accelerator API, and once imported, they can be customized and published within the governance framework. This approach provides the flexibility required for various enterprise governance models.

Training Data Statistics: Watson OpenScale needs to understand the characteristics of the data the model was trained on. This includes things like the distribution of features, sensitive attributes (for fairness monitoring), and how the model performed on this initial data. These 'training data statistics' are crucial for:

Fairness Configuration: Recommending fairness attributes, reference, and monitored groups.

Bias Detection: Calculating fairness metrics (like disparate impact) by comparing runtime behavior to the learned training data distribution.

Explainability: Generating explanations by understanding the distribution of values in the training data to create meaningful perturbations.

Drift Detection: Building a drift detection model that compares runtime data to the training data to identify shifts.

While Watson OpenScale also consumes payload data (the data sent to the deployed model for predictions) at runtime to calculate various metrics and perform monitoring, the initial setup and the ability to generate meaningful statistics for things like fairness and drift fundamentally rely on understanding the training data

Customization of Knowledge Accelerators in IBM Cloud Pak for Data is a structured process to preserve the integrity of base content while allowing for extension. The recommended approaches include:

Creating a separate project for customizations, so that changes are isolated and easily managed without affecting the source accelerator.

Using a 'development' vocabulary where custom terms and structures are created. This is separate from the 'enterprise vocabulary,' which contains the unmodified, original Knowledge Accelerator content.

Inline editing of the original content is discouraged. Use of GitHub or namespaces is not part of the official customization workflow.

Cloud Pak for Data provides audit logging capabilities via the Audit Logging Service, which uses Fluentd to collect, process, and forward log data to external SIEM solutions. Fluentd input streams are configured to export audit records in real time. While Splunk and QRadar are common integrations, Log360 is not explicitly listed in the official supported list. Each SIEM connection can be configured independently, and while audit logging is widely supported, it may not be enabled by default for every single service---therefore only option B is correct.

'You can create a maximum of 10 instances per deployment. After you reach the maximum number, the New instance button is not displayed in IBM Cloud Pak for Data.'