AIF-C01 practice questions 181–190

1. Question 181 · 417 in bank

   A financial company wants to flag all credit card activity as possibly fraudulent or non-fraudulent based on transaction data. Which type of ML model meets these requirements?

   • ARegression
   • BDiffusion
   • CBinary classification
   • DMulti-class classification

   Show answer

   Answer: C

   Next question

2. Question 182 · 417 in bank

   A hospital wants to use a generative AI solution with speech-to-text functionality to help improve employee skills in dictating clinical notes. Which AWS service meets these requirements?

   • AAmazon Q Developer
   • BAmazon Polly
   • CAmazon Rekognition
   • DAWS HealthScribe

   Show answer

   Answer: D

   Next question

3. Question 183 · 417 in bank

   Which type of AI model makes numeric predictions?

   • ADiffusion
   • BRegression
   • CTransformer
   • DMulti-modal

   Show answer

   Answer: B

   Next question

4. Question 184 · 417 in bank

   What is the purpose of vector embeddings in a large language model (LLM)?

   • ASplitting text into manageable pieces of data
   • BGrouping a set of characters to be treated as a single unit
   • CProviding the ability to mathematically compare texts
   • DProviding the count of every word in the input

   Show answer

   Answer: C

   Next question

5. Question 185 · 417 in bank

   Select 2

   A company wants to fine-tune a foundation model (FM) by using AWS services. The company needs to ensure that its data stays private, safe, and secure in the source AWS Region where the data is stored. Which combination of steps will meet these requirements MOST cost-effectively? (Choose two.)

   • AHost the model on premises by using AWS Outposts.
   • BUse the Amazon Bedrock API.
   • CUse AWS PrivateLink and a VPC.
   • DHost the Amazon Bedrock API on premises.
   • EUse Amazon CloudWatch logs and metrics.

   Show answer

   Answer: BC

   Next question

6. Question 186 · 417 in bank

   A financial company uses AWS to host its generative AI models. The company must generate reports to show adherence to international regulations for handling sensitive customer data. Which AWS service meets these requirements?

   • AAmazon Macie
   • BAWS Artifact
   • CAWS Secrets Manager
   • DAWS Config

   Show answer

   Answer: B

   Next question

7. Question 187 · 417 in bank

   A medical company wants to modernize its onsite information processing application. The company wants to use generative AI to respond to medical questions from patients. Which AWS service should the company use to ensure responsible AI for the application?

   • AGuardrails for Amazon Bedrock
   • BAmazon Inspector
   • CAmazon Rekognition
   • DAWS Trusted Advisor

   Show answer

   Answer: A

   Next question

8. Question 188 · 417 in bank

   Which metric is used to evaluate the performance of foundation models (FMs) for text summarization tasks?

   • AF1 score
   • BBilingual Evaluation Understudy (BLEU) score
   • CAccuracy
   • DMean squared error (MSE)

   Show answer

   Answer: B

   Next question

9. Question 189 · 417 in bank

   What is the benefit of fine-tuning a foundation model (FM)?

   • AFine-tuning reduces the FM's size and complexity and enables slower inference.
   • BFine-tuning uses specific training data to retrain the FM from scratch to adapt to a specific use case.
   • CFine-tuning keeps the FM's knowledge up to date by pre-training the FM on more recent data.
   • DFine-tuning improves the performance of the FM on a specific task by further training the FM on new labeled data.

   Show answer

   Answer: D

   Next question

10. Question 190 · 417 in bank

    A company wants to improve its chatbot's responses to match the company's desired tone. The company has 100 examples of high-quality conversations between customer service agents and customers. The company wants to use this data to incorporate company tone into the chatbot's responses. Which solution meets these requirements?

    • AUse Amazon Personalize to generate responses.
    • BCreate an Amazon SageMaker HyperPod pre-training job.
    • CHost the model by using Amazon SageMaker. Use TensorRT for large language model (LLM) deployment.
    • DCreate an Amazon Bedrock fine-tuning job.

    Show answer

    Answer: D

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AIF-C01 practice, question 181. 417 questions available.