Amazon AIF-C01 Online Practice Questions and Exam Preparation

Amazon AIF-C01 Online Questions & Answers

• Question 81:

  A company is building a generative AI application with a foundation model (FM). The application needs to automatically generate marketing emails. The company wants the application's output text to be creative and short in length.

  Which configuration of inference parameters will meet these requirements?

  A. Decrease the temperature and the response length.
  B. Increase the temperature and the response length.
  C. Increase the temperature and decrease the response length.
  D. Decrease the temperature and increase the response length.
  C. Increase the temperature and decrease the response length.

  ---

  Explanation

  Increasing the temperature encourages more creative and diverse text generation, while decreasing the response length constrains the output to be short, which fits the requirement for creative, concise marketing emails.

• Question 82:

  What are tokens in the context of generative AI models?

  A. Tokens are the basic units of input and output that a generative AI model operates on, representing words, subwords, or other linguistic units.
  B. Tokens are the mathematical representations of words or concepts used in generative AI models.
  C. Tokens are the pre-trained weights of a generative AI model that are fine-tuned for specific tasks.
  D. Tokens are the specific prompts or instructions given to a generative AI model to generate output.
  A. Tokens are the basic units of input and output that a generative AI model operates on, representing words, subwords, or other linguistic units.

  ---

  Tokens in generative AI models are the smallest units that the model processes, typically representing words, subwords, or characters. They are essential for the model to understand and generate language, breaking down text into manageable parts for processing.

  Option A (Correct): "Tokens are the basic units of input and output that a generative AI model operates on, representing words, subwords, or other linguistic units":This is the correct definition of tokens in the context of generative AI models.

  Option B:"Mathematical representations of words" describes embeddings, not tokens.

  Option C:"Pre-trained weights of a model" refers to the parameters of a model, not tokens.

  Option D:"Prompts or instructions given to a model" refers to the queries or commands provided to a model, not tokens.

  References:

  Understanding Tokens in NLP:AWS provides detailed explanations of how tokens are used in natural language processing tasks by AI models, such as in Amazon Comprehend and other AWS AI services.

• Question 83:

  A company is using Amazon SageMaker Studio notebooks to build and train ML models. The company stores the data in an Amazon S3 bucket. The company needs to manage the flow of data from Amazon S3 to SageMaker Studio notebooks. Which solution will meet this requirement?

  A. Use Amazon Inspector to monitor SageMaker Studio.
  B. Use Amazon Macie to monitor SageMaker Studio.
  C. Configure SageMaker to use a VPC with an S3 endpoint.
  D. Configure SageMaker to use S3 Glacier Deep Archive.
  C. Configure SageMaker to use a VPC with an S3 endpoint.

  ---

  To manage the flow of data from Amazon S3 to SageMaker Studio notebooks securely, using a VPC with an S3 endpoint is the best solution.

• Question 84:

  A company has installed a security camera. The company uses an ML model to evaluate the security camera footage for potential thefts. The company has discovered that the model disproportionately flags people who are members of a specific ethnic group. Which type of bias is affecting the model output?

  A. Measurement bias
  B. Sampling bias
  C. Observer bias
  D. Confirmation bias
  B. Sampling bias

  ---

  Sampling bias is the correct type of bias affecting the model output when it disproportionately flags people from a specific ethnic group.

• Question 85:

  A company uses Amazon Bedrock to generate marketing summaries. Some outputs contain outdated information. The team wants the model to use the latest internal data sources. Which solution will improve output freshness?

  A. Increase max tokens
  B. Add few-shot examples to the prompt
  C. Use Retrieval Augmented Generation (RAG)
  D. Reduce the temperature
  C. Use Retrieval Augmented Generation (RAG)

  ---

  RAG integrates real-time or frequently updated documents through a vector store. This ensures the model pulls the most recent information at inference time, solving issues with outdated or static model knowledge.

• Question 86:

  A company is using a foundation model (FM) to generate creative marketing slogans for various products. The company wants to reuse a standard template with common instructions when generating slogans for different products. However, the company needs to add short descriptions for each product.

  Which Amazon Bedrock solution will meet these requirements?

  A. Prompt management
  B. Knowledge Bases
  C. Model evaluation
  D. Cross-region inference
  A. Prompt management

  ---

  Explanation

  Prompt management in Amazon Bedrock allows reuse of standardized prompt templates while dynamically inserting variable inputs, such as product descriptions, to generate consistent outputs across different use cases.

• Question 87:

  A company is developing an ML model to predict customer churn.

  Which evaluation metric will assess the model's performance on a binary classification task such as predicting chum?

  A. F1 score
  B. Mean squared error (MSE)
  C. R-squared
  D. Time used to train the model
  A. F1 score

  ---

  For binary classification tasks like churn prediction, the F1 score balances precision and recall into a single metric, making it ideal for evaluating how well the model identifies churners without over- or under-predicting.

• Question 88:

  A financial company stores patterns of fraudulent behavior in a database. The company uses this data to conduct investigations.

  The company wants to use a graph-based ML solution to develop an AI tool that helps with these investigations.

  Which AWS service will meet these requirements?

  A. Amazon OpenSearch Service
  B. Amazon Aurora
  C. Amazon Neptune
  D. Amazon MemoryDB
  C. Amazon Neptune

  ---

  Explanation

  Amazon Neptune is a fully managed graph database service designed for graph-based data models and graph analytics, making it suitable for building ML solutions that analyze relationships and patterns such as fraudulent behavior networks for investigation purposes.

• Question 89:

  A company has a database of petabytes of unstructured data from internal sources. The company wants to transform this data into a structured format so that its data scientists can perform machine learning (ML) tasks. Which service will meet these requirements?

  A. Amazon Lex
  B. Amazon Rekognition
  C. Amazon Kinesis Data Streams
  D. AWS Glue
  D. AWS Glue

  ---

  AWS Glue is the correct service for transforming petabytes of unstructured data into a structured format suitable for machine learning tasks.

• Question 90:

  A company uses Amazon Bedrock for its generative AI application. The company wants to use Amazon Bedrock Guardrails to detect and filter harmful user inputs and model-generated outputs. Which content categories can the guardrails filter? (Choose two.)

  A. Hate
  B. Politics
  C. Violence
  D. Gambling
  E. Religion
  A. Hate
  C. Violence

  ---

  Amazon Bedrock Guardrails provide configurable content filters to detect and block harmful content in generative AI applications. Specifically, they include filters for categories such as Hate and Violence, among others. These filters can be applied to both user inputs and model-generated outputs to ensure that the AI application adheres to responsible AI practices and organizational policies.