Oracle Oracle Certifications 1Z0-1110-22 Questions & Answers

• Question 11:

  You are asked to prepare data for a custom-built model that requires transcribing Spanish video recordings into a readable text format with profane words identified. Which Oracle Cloud service would you use?

  A. OCI Translation

  B. OCI Language

  C. OCI Anomaly Detection

  D. OCI Speech

  Correct Answer: D

• Question 12:

  You want to write a Python script to create a collection of different projects for your data sci-ence team. Which Oracle Cloud Infrastructure (OCI) Data Science Interface would you use?

  A. Programming Language Software Development Kit (SDK)

  B. Mobile App

  C. Command Line Interface (CLI)

  D. OCI Console

  Correct Answer: A

• Question 13:

  You are a data scientist working for a manufacturing company, you have developed a fore- casting model to predict the sales demand in the upcoming months. You created a model artifact that contained custom logic requiring third party libraries. When you deployed the model, it failed to run because you did not include all the third-party dependencies in the model artifact.?

  A. Score.py

  B. Runtime.yaml

  C. Requirement.txt

  D. Model_artifact_validate.py

  Correct Answer: C

• Question 14:

  You have just received a new data set from a colleague. You want to quickly find out summary information about the data set, such as the types of features, total number of observations, and datadistributions, Which Accelerated Data Science (ADS) SDK method from the ADandDataset class would you use?

  A. Show_in_notebook{}

  B. To_xgb{}

  C. Compute{}

  D. Show_corr{}

  Correct Answer: A

• Question 15:

  You are a computer vision engineer building an image recognition model. You decide to use Oracle Data Labeling to annotate your image data. Which of the following THREE are possible ways to annotate an image in Data Labeling?

  A. Adding labels to image using semantic segmentation, by drawing multiple bounding boxes to an image.

  B. Adding a single label to an image.

  C. Adding labels to an image by drawing bounding box to an image, is not supported by Data Labeling

  D. Adding labels to an image using object detection, by drawing bounding boxes to an im- age.

  E. Adding multiple labels to an image.

  Correct Answer: BDE

• Question 16:

  As a data scientist, you are tasked with creating a model training job that is expected to take different hyperparameter values on every run. What is the most efficient way to set those pa-rameters with Oracle Data Science Jobs?

  A. Create a new job every time you need to run your code and pass the parameters as en- vironment variables.

  B. Create your code to expect different parameters as command line arguments, and create it new job every time you run the code.

  C. Create your code to expect different parameters either as environment variables or as command line arguments, which are set on every job run with different values.

  D. Create a new no by setting the required parameters in your code, and create a new job for mery code change.

  Correct Answer: C

• Question 17:

  You have created a model, and you want to use the Accelerated Data Science (ADS) SDK to deploy this model. Where can you save the artifacts to deploy this model with ADS?

  A. Model Depository

  B. Model Catalog

  C. OCI Vault

  D. Data Science Artifactory

  Correct Answer: B

• Question 18:

  You are building a model and need input that represents data as morning, afternoon, or evening. However, the data contains a time stamp. What part of the Data Science life cycle would you be in when creating the new variable?

  A. Model type selection

  B. Model validation

  C. Data access

  D. Feature engineering

  Correct Answer: B

• Question 19:

  You realize that your model deployment is about to reach its utilization limit. What would you do to avoid the issue before requests start to fail?

  A. Update the deployment to use fewer instances.

  B. Delete the deployment.

  C. Reduce the load balancer bandwidth limit so that fewer requests come in.

  D. Update the deployment to use a larger virtual machine (mare CPUs/memory).

  E. Update the deployment to add more instances.

  Correct Answer: E

• Question 20:

  You are creating an Oracle Cloud Infrastructure (OCI) Data Science job that will run on a recurring basis in a production environment. This job will pick up sensitive data from an Object Storage bucket, train a model, and save it to the model catalog. How would you design the authentication mechanism for the job?

  A. Package your personal OC file and keys in the job artifact.

  B. Use the resource principal of the job run as the signer in the job code, ensuring there is a dynamic group for this job run with appropriate access to Object Storage and the model catalog.

  C. Store your personal OCI config file and kays in the Vault, and access the Vault through the job nun resource principal

  D. Create a pre-authenticated request (PAA) for the Object Storage bucket, and use that in the job code.

  Correct Answer: B