A company creates video content. The company wants to use generative AI to generate new creative content and to reduce video creation time.
Which solution will meet these requirements in the MOST operationally efficient way?
A. Use the Amazon Titan Image Generator model on Amazon Bedrock to generate intermediate images. Use video editing software to create videos.
B. Use the Amazon Nova Canvas model on Amazon Bedrock to generate intermediate images. Use video editing software to create videos.
C. Use the Amazon Nova Reel model on Amazon Bedrock to generate videos.
D. Use the Amazon Nova Pro model on Amazon Bedrock to generate videos.
Show Answer
Correct Answer: C
Explanation: Amazon Nova Reel is the Amazon Bedrock model specifically designed for AI video generation. It can generate videos directly from prompts (and supported inputs), avoiding the extra steps of generating still images and assembling them with video editing software. That makes it the most operationally efficient solution. Amazon Titan Image Generator and Amazon Nova Canvas are image-generation models, while Amazon Nova Pro is a general multimodal foundation model rather than a dedicated video-generation model.
Question 185
A company is introducing a new feature for its application. The feature will refine the style of output messages. The company will fine-tune a large language model (LLM) on Amazon Bedrock to implement the feature.
Which type of data does the company need to meet these requirements?
A. Samples of only input messages
B. Samples of only output messages
C. Samples of pairs of input and output messages
D. Separate samples of input and output messages
Show Answer
Correct Answer: C
Explanation: The correct data for supervised fine-tuning of a large language model on Amazon Bedrock is paired input-output examples. The model learns the desired transformation (such as refining the style of output messages) by mapping each input prompt to its corresponding target output. Input-only, output-only, or unpaired datasets do not provide the supervision needed for fine-tuning.
Question 186
HOTSPOT
-
A company is developing an AI application to help the company approve or deny personal loans. The application must follow the principles of responsible AI.
Select the correct responsible AI principle from the following list for each action. Select each responsible AI principle one time or not at all.
Show Answer
Correct Answer: Privacy and security
Fairness
Robustness
Explanation: Encrypting data and isolating the application addresses privacy and security. Evaluating impacts across different population groups addresses fairness by checking for bias and equitable outcomes. Testing with unexpected data ensures the system remains reliable under unusual conditions, which is robustness.
Question 187
A company is using supervised learning to train an AI model on a small labeled dataset that is specific to a target task.
Which step of the foundation model (FM) lifecycle does this describe?
A. Fine-tuning
B. Data selection
C. Pre-training
D. Evaluation
Show Answer
Correct Answer: A
Explanation: Training a foundation model with supervised learning on a small labeled dataset tailored to a specific downstream task is the fine-tuning stage. Pre-training uses very large datasets (often unlabeled), data selection is the preparation stage, and evaluation measures model performance after training.
Question 188
A company wants to build and deploy ML models on AWS without writing any code.
Which AWS service or feature meets these requirements?
A. Amazon SageMaker Canvas
B. Amazon Rekognition
C. AWS DeepRacer
D. Amazon Comprehend
Show Answer
Correct Answer: A
Explanation: Amazon SageMaker Canvas is a no-code machine learning service that enables users to build, train, and deploy/publish ML models and generate predictions through a visual interface. Amazon Rekognition and Amazon Comprehend provide prebuilt AI APIs for specific use cases rather than general no-code model building, and AWS DeepRacer is a learning platform for reinforcement learning.
Question 189
A company wants to label training datasets by using human feedback to fine-tune a foundation model (FM). The company does not want to develop labeling applications or manage a labeling workforce.
Which AWS service or feature meets these requirements?
A. Amazon SageMaker Data Wrangler
B. Amazon SageMaker Ground Truth Plus
C. Amazon Transcribe
D. Amazon Macie
Show Answer
Correct Answer: B
Explanation: Amazon SageMaker Ground Truth Plus is a fully managed data labeling service in which AWS provides the labeling workflows and manages the labeling workforce. It is designed for creating high-quality labeled datasets, including datasets for human feedback used to fine-tune foundation models, without requiring customers to build labeling applications or manage annotators.
Question 190
A healthcare company wants to analyze patient data. The data was gathered over the previous year to detect patterns in disease outbreaks. The company needs to create a trend analysis report for each month to present to public health officials. The company must provide insights into patient data from the most recent month of the current year.
Which inference method will meet these requirements MOST cost-effectively?
A. Real-time inference
B. Batch transform
C. Serverless inference
D. Asynchronous inference
Show Answer
Correct Answer: B
Explanation: Batch transform is the most cost-effective choice for periodic inference over large historical datasets. The use case is to generate monthly trend analysis reports using accumulated patient data, not to serve low-latency predictions. Real-time, serverless, and asynchronous inference are endpoint-based options intended for online inference workloads, whereas Batch Transform is designed for offline, scheduled processing at scale.
Question 191
Which AWS service or feature stores embeddings in a vector database for use with foundation models (FMs) and Retrieval Augmented Generation (RAG)?
A. Amazon SageMaker Ground Truth
B. Amazon OpenSearch Service
C. Amazon Transcribe
D. Amazon Textract
Show Answer
Correct Answer: B
Explanation: Amazon OpenSearch Service supports vector search and can store embeddings in a vector index, making it suitable for Retrieval Augmented Generation (RAG) workflows with foundation models. The other options provide data labeling (SageMaker Ground Truth), speech-to-text (Transcribe), and document text extraction (Textract), not vector database storage.
Question 192
HOTSPOT
-
An AI practitioner is determining the appropriate data type for various use cases.
Select the correct data type from the following list for each use case. Select each data type one time.
Show Answer
Correct Answer: Build a sentiment analysis model for social media posts. → Text data
Train a self-driving car to recognize traffic signs. → Image data
Optimize ad campaigns using customer demographic data and purchase history. → Tabular data
Forecast stock prices by using historical price data. → Time series data
Explanation: Sentiment analysis processes text, traffic sign recognition uses images, customer demographics and purchase history are structured tabular records, and historical stock prices are sequential time-based data.
Question 193
An online media streaming company wants to give its customers the ability to perform natural language-based image search and filtering. The company needs a vector database that can help with similarity searches and nearest neighbor queries.
Which AWS service meets these requirements?
A. Amazon Comprehend
B. Amazon Personalize
C. Amazon Polly
D. Amazon OpenSearch Service
Show Answer
Correct Answer: D
Explanation: Amazon OpenSearch Service supports vector search capabilities, including k-nearest neighbor (k-NN) search over vector embeddings, making it suitable as a vector database for natural language-based image search, similarity searches, and nearest neighbor queries. Amazon Comprehend is for NLP, Amazon Personalize is for recommendations, and Amazon Polly is for text-to-speech.
$19
Get all 443 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
