WorksheetsQuiz A_3
Total questions: 20
Worksheet time: 10mins
A company is training a foundation model (FM). The company wants to increase the accuracy of the model up to a specific acceptance level Which solution will meet these requirements?
Decrease the batch size
Increase the epochs
Decrease the epoxy
Increase the temperature parameter
A company is building a large language model (LLM) question answering chatbot. The company wants to decrease the number of actions call center employees need to take to respond to customer questions Which business objective should the company use to evaluate the effect of the LLM chatbot
Website engagement rate
Average call duration
Corporate social responsibility
Regulatory compliance
Which functionality does Amazon SageMaker Clarify provide?
Integrates Retrieval Augmented Generation (RAG) workflow
Monitors the quality of ML models in production
Documents critical details about ML models
Identifies potential bias during data preparation
A company is developing a new model to predict the prices of specific items. The model performed well on the training data set. When the company deployed the model to production, the model's performance decreased significantly What should the company do to mitigate this problem
Reduce the volume of data that is used in training
Add hyperparameters to the model
Increase the volume of data that is used in training
Increase the model training time
An ecommerce company wants to build a solution to determine customer sentiments based on written customer reviews of products. Which AWS service meet these requirements? (choose two)
Amazon Lex
Amazon Comprehend
Amazon Polly
Amazon Bedrock
Amazon Rekognition
A company wants to use large language model (LLMS) with Amazon Bedrock to develop a chat interface for the company's product manuals. These manuals are stored as PDF files Which solution meets these requirements MOST cost-effectively?
Use prompt engineering to add one PDF file as context to the user prompt when the prompt is submitted to Amazon Bedrock
Use prompt engineering to add all the PDF files as context to the user prompt when the prompt is submitted to Amazon Bedrock
Use all the PDF documents to fine-tune a model with Amazon Bedrock. Use fine-tune model to process user prompts
Upload PDF documents to an Amazon Bedrock knowledge base. Use the knowledge base to provide context when user submit prompts to Amazon Bedrock
A social media company wants to use a large language model (LLM) for content moderation. The company wants to evaluate the LLM outputs for bias and potential discrimination against specific groups or individuals Which data source should the company use to evaluate the LLM outputs with the LEAST administrative effort
User generated content
Moderation logs
Content moderation guidelines
Benchmark datasets
A company wants to use a pre-trained generative AI model to generate content for its marketing campaigns. The company needs to ensure that the generated content aligns with the company's brands voice and messaging requirements Which solution meets these requirements?
Optimize the model’s architecture and hyperparameters to improve the model's overall performance
Increase the model's complexity by adding more layers to the model’s architecture
Create effective prompts that provide clear instructions and context to guide the model’s generation
Select a large, diverse data set to pre-train a new generative model
A loan company is building a generative AI-based solution to offer new applicants discounts based on specific business criteria. The company wants to build and use an AI model responsibly to minimize bias that could negatively affect some customers Which actions should the company take to meet these requirements? (choose two)
Detect imbalances or disparities in the data
Ensure that the model runs frequently
Evaluate the model's behavior so that the company can provide transparency to stakeholders
Use the Recall Oriented Understudy for Gisting Evaluation (ROUGE) technique to ensure that the model is 100% accurate
Ensure that the model’s inference time is within the accepted limits
A company is using an Amazon Bedrock based model to summarize documents for an internal use case. The company trained a custom model to improve the summarization quality Which action must the company take to use the custom model through Amazon Bedrock?
Purchase Provisioned Throughput for the custom model
Deploy the custom model in Amazon SageMaker endpoint for real-time inference
Register the model with the Amazon SageMaker Model Registry
Grant access to in Amazon Bedrock
A company needs to choose a model from Amazon Bedrock to use internally. The company must identify a model that generates responses in a style that the company’s employees prefer What should the company do to meet these requirements
Evaluate the models by using built in prompt datasets
Evaluate the models by using a human work first and custom prompt datasets
Use public model leaderboards to identify the model
Use the model invocation latency runtime metrics in Amazon cloud watch when trying models
A student at a university is copying content from generative AI to write essays Which challenge of responsible generative AI does this scenario represent?
Toxicity
Hallucinations
Plagiarism
Privacy
A company needs to build its own large language model (LLM) based on only the company's private data. The company is concerned about environmental effect of the training process Which Amazon EC2 instance type has the LEAST environmental effect when training LLMs?
Amazon EC2 C series
Amazon EC2 G series
Amazon EC2 P series
Amazon EC2 Trn series
A company wants to build an interactive application for children that generates new stories based on classic stories. The company wants to use Amazon Bedrock and needs to ensure that their results are topics that appropriated for children Which AWS service or feature will meet these requirements?
Amazon Rekognition
Amazon Bedrock playgrounds
Guardrails for Amazon Bedrock
Agents for Amazon Bedrock
A company is building an application that needs to generate synthetic data that is based on existing data which type of model can the company use to meet this requirement
Generative Adversarial Network (GAN)
XGBoost
Residual neural network
Wavenet
A digital devices company wants to predict customer demand for memory hardware. The company does not have coding experience or knowledge of ML algorithms and needs help to develop a data-driven predictive model. The company needs to perform analysis on internal data and external data Which solution will meet these requirements?
Store data in Amazon S3. Create ML models and demand forecast predictions by using Amazon SageMaker built in algorithms that use the data from Amazon S3
Import the data into Amazon Sage Maker Data Wrangler. Create models and demand forecast prediction by using Sage Maker built in algorithms
Import the data into Amazon Sage Maker Data Wrangler. Build ML models and demand forecast predictions by using an Amazon Personalized Trending-Now recipe
Import the data into Amazon Sage Maker Canvas. Build ML models and demand forecast predictions by selecting the values in the data from Sage Maker Canvas
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?
Measurement bias
Sampling bias
Observer bias
Confirmation bias
A company is building a customer service chat box. The company wants the chat bot to improve its responses by learning from past interactions and online resources Which AI learning strategy provides this self improvement capability?
Supervised learning with a manually curated data set of good responses and bad responses
Reinforcement learning with reward for positive customer feedback
Unsupervised learning to find clusters of similar customer inquiries
Supervised learning with a continuously updated FAQ database
An AI practitioner has built a deep learning model to classify the types of materials in images. The AI practitioner now wants to measure the model performance Which metric will help the AI practitioner evaluate the performance of the model?
Confusion matrix
Correlation matrix
R2 score
Mean squared error (MSE)
A company has built a chat bot that can respond to natural language questions with images. The company wants to ensure that the chatbot does not return inappropriate or unwanted images Which solution will meet these requirements?
Implement moderation APIs
Retrain the model with a general public data set
Perform model validation
Automate user feedback integration
