mio

A company makes forecasts each quarter to decide how to optimize operations to meet expected demand. The company uses ML models to make these forecasts. An AI practitioner is writing a report about the trained ML models to provide transparency and explainability to company stakeholders. What should the AI practitioner include in the report to meet the transparency and explainability requirements?. Code for model training. Partial dependence plots (PDPs). Sample data for training. Model convergence tables.

A law firm wants to build an AI application by using large language models (LLMs). The application will read legal documents and extract key points from the documents. Which solution meets these requirements?. Build an automatic named entity recognition system. Create a recommendation engine. Develop a summarization chatbot. Develop a multi-language translation system.

A company wants to classify human genes into 20 categories based on gene characteristics. The company needs an ML algorithm to document how the inner mechanism of the model affects the output. Which ML algorithm meets these requirements?. Decision trees. Linear regression. Logistic regression. Neural networks.

A company has built an image classification model to predict plant diseases from photos of plant leaves. The company wants to evaluate how many images the model classified correctly. Which evaluation metric should the company use to measure the model's performance?. R-squared score. Accuracy. Root mean squared error (RMSE). Learning rate.

A company is using a pre-trained large language model (LLM) to build a chatbot for product recommendations. The company needs the LLM outputs to be short and written in a specific language. Which solution will align the LLM response quality with the company's expectations?. Adjust the prompt. Choose an LLM of a different size. Increase the temperature. Increase the Top K value.

A company uses Amazon SageMaker for its ML pipeline in a production environment. The company has large input data sizes up to 1 GB and processing times up to 1 hour. The company needs near real-time latency. Which SageMaker inference option meets these requirements?. Real-time inference. Serverless inference. Asynchronous inference. Batch transform.

A company is using domain-specific models. The company wants to avoid creating new models from the beginning. The company instead wants to adapt pre-trained models to create models for new, related tasks. Which ML strategy meets these requirements?. Increase the number of epochs. Use transfer learning. Decrease the number of epochs. Use unsupervised learning.

A company is building a solution to generate images for protective eyewear. The solution must have high accuracy and must minimize the risk of incorrect annotations. Which solution will meet these requirements?. Human-in-the-loop validation by using Amazon SageMaker Ground Truth Plus. Data augmentation by using an Amazon Bedrock knowledge base. Image recognition by using Amazon Rekognition. Data summarization by using Amazon QuickSight Q.

A company wants to create a chatbot by using a foundation model (FM) on Amazon Bedrock. The FM needs to access encrypted data that is stored in an Amazon S3 bucket. The data is encrypted with Amazon S3 managed keys (SSE-S3). The FM encounters a failure when attempting to access the S3 bucket data. Which solution will meet these requirements?. Ensure that the role that Amazon Bedrock assumes has permission to decrypt data with the correct encryption key. Set the access permissions for the S3 buckets to allow public access to enable access over the internet. Use prompt engineering techniques to tell the model to look for information in Amazon S3. Ensure that the S3 data does not contain sensitive information.

A company wants to use language models to create an application for inference on edge devices. The inference must have the lowest latency possible. Which solution will meet these requirements?. Deploy optimized small language models (SLMs) on edge devices. Deploy optimized large language models (LLMs) on edge devices. Incorporate a centralized small language model (SLM) API for asynchronous communication with edge devices. Incorporate a centralized large language model (LLM) API for asynchronous communication with edge devices.

A company wants to build an ML model by using Amazon SageMaker. The company needs to share and manage variables for model development across multiple teams. Which SageMaker feature meets these requirements?. Amazon SageMaker Feature Store. Amazon SageMaker Data Wrangler. Amazon SageMaker Clarify. Amazon SageMaker Model Cards.

A company wants to use generative AI to increase developer productivity and software development. The company wants to use Amazon Q Developer. What can Amazon Q Developer do to help the company meet these requirements?. Create software snippets, reference tracking, and open source license tracking. Run an application without provisioning or managing servers. Enable voice commands for coding and providing natural language search. Convert audio files to text documents by using ML models.

A financial institution is using Amazon Bedrock to develop an AI application. The application is hosted in a VPC. To meet regulatory compliance standards, the VPC is not allowed access to any internet traffic. Which AWS service or feature will meet these requirements?. AWS PrivateLink. Amazon Macie. Amazon CloudFront. Internet gateway.

A company wants to develop an educational game where users answer questions such as the following: "A jar contains six red, four green, and three yellow marbles. What is the probability of choosing a green marble from the jar?" Which solution meets these requirements with the LEAST operational overhead?. Use supervised learning to create a regression model that will predict probability. Use reinforcement learning to train a model to return the probability. Use code that will calculate probability by using simple rules and computations. Use unsupervised learning to create a model that will estimate probability density.

Which metric measures the runtime efficiency of operating AI models?. Customer satisfaction score (CSAT). Training time for each epoch. Average response time. Number of training instances.

A company is building a contact center application and wants to gain insights from customer conversations. The company wants to analyze and extract key information from the audio of the customer calls. Which solution meets these requirements?. Build a conversational chatbot by using Amazon Lex. Transcribe call recordings by using Amazon Transcribe. Extract information from call recordings by using Amazon SageMaker Model Monitor. Create classification labels by using Amazon Comprehend.

A company has petabytes of unlabeled customer data to use for an advertisement campaign. The company wants to classify its customers into tiers to advertise and promote the company's products. Which methodology should the company use to meet these requirements?. Supervised learning. Unsupervised learning. Reinforcement learning. Reinforcement learning from human feedback (RLHF).

An AI practitioner wants to use a foundation model (FM) to design a search application. The search application must handle queries that have text and images. Which type of FM should the AI practitioner use to power the search application?. Multi-modal embedding model. Text embedding model. Multi-modal generation model. Image generation model.

A company uses a foundation model (FM) from Amazon Bedrock for an AI search tool. The company wants to fine-tune the model to be more accurate by using the company's data. Which strategy will successfully fine-tune the model?. Provide labeled data with the prompt field and the completion field. Prepare the training dataset by creating a .txt file that contains multiple lines in .csv format. Purchase Provisioned Throughput for Amazon Bedrock. Train the model on journals and textbooks.

A company wants to use AI to protect its application from threats. The AI solution needs to check if an IP address is from a suspicious source. Which solution meets these requirements?. Build a speech recognition system. Create a natural language processing (NLP) named entity recognition system. Develop an anomaly detection system. Create a fraud forecasting system.

Which feature of Amazon OpenSearch Service gives companies the ability to build vector database applications?. Integration with Amazon S3 for object storage. Support for geospatial indexing and queries. Scalable index management and nearest neighbor search capability. Ability to perform real-time analysis on streaming data.

Which option is a use case for generative AI models?. Improving network security by using intrusion detection systems. Creating photorealistic images from text descriptions for digital marketing. Enhancing database performance by using optimized indexing. Analyzing financial data to forecast stock market trends.

A company wants to build a generative AI application by using Amazon Bedrock and needs to choose a foundation model (FM). The company wants to know how much information can fit into one prompt. Which consideration will inform the company's decision?. Temperature. Context window. Batch size. Model size.

A company wants to make a chatbot to help customers. The chatbot will help solve technical problems without human intervention. The company chose a foundation model (FM) for the chatbot. The chatbot needs to produce responses that adhere to company tone. Which solution meets these requirements?. Set a low limit on the number of tokens the FM can produce. Use batch inferencing to process detailed responses. Experiment and refine the prompt until the FM produces the desired responses. Define a higher number for the temperature parameter.

An online learning company has large volumes of educational material and wants enterprise search across it. Which AWS service fits?. Amazon Kendra. Amazon Polly. Amazon Textract. Amazon Comprehend.

A company wants to use a large language model (LLM) on Amazon Bedrock for sentiment analysis. The company wants to classify the sentiment of text passages as positive or negative. Which prompt engineering strategy meets these requirements?. Provide examples of text passages with corresponding positive or negative labels in the prompt followed by the new text passage to be classified. Provide a detailed explanation of sentiment analysis and how LLMs work in the prompt. Provide the new text passage to be classified without any additional context or examples. Provide the new text passage with a few examples of unrelated tasks, such as text summarization or question answering.

A security company is using Amazon Bedrock to run foundation models (FMs). The company wants to ensure that only authorized users invoke the models. The company needs to identify any unauthorized access attempts to set appropriate AWS Identity and Access Management (IAM) policies and roles for future iterations of the FMs. Which AWS service should the company use to identify unauthorized users that are trying to access Amazon Bedrock?. AWS Audit Manager. AWS CloudTrail. Amazon Fraud Detector. AWS Trusted Advisor.

A company has developed an ML model for image classification. The company wants to deploy the model to production so that a web application can use the model. The company needs to implement a solution to host the model and serve predictions without managing any of the underlying infrastructure. Which solution will meet these requirements?. Use Amazon SageMaker Serverless Inference to deploy the model. Use Amazon CloudFront to deploy the model. Use Amazon API Gateway to host the model and serve predictions. Use AWS Batch to host the model and serve predictions.

An AI company periodically evaluates its systems and processes with the help of independent software vendors (ISVs). The company needs to receive email message notifications when an ISV's compliance reports become available. Which AWS service can the company use to meet this requirement?. AWS Audit Manager. AWS Artifact. AWS Trusted Advisor. AWS Data Exchange.

A company wants to use a large language model (LLM) to develop a conversational agent. The company needs to prevent the LLM from being manipulated with common prompt engineering techniques to perform undesirable actions or expose sensitive information. Which action will reduce these risks?. Create a prompt template that teaches the LLM to detect attack patterns. Increase the temperature parameter on invocation requests to the LLM. Avoid using LLMs that are not listed in Amazon SageMaker. Decrease the number of input tokens on invocations of the LLM.

A company is using the Generative AI Security Scoping Matrix to assess security responsibilities for its solutions. The company has identified four different solution scopes based on the matrix. Which solution scope gives the company the MOST ownership of security responsibilities?. Using a third-party enterprise application that has embedded generative AI features. Building an application by using an existing third-party generative AI foundation model (FM). Refining an existing third-party generative AI foundation model (FM) by fine-tuning the model by using data specific to the business. Building and training a generative AI model from scratch by using specific data that a customer owns.

A travel company uses a pre-trained large language model (LLM) to power a booking assistant. The company needs the assistant's replies to be brief and written in a particular language. Which approach will best align the LLM's output with these expectations?. Refining the prompt. Increase the top K Value. Choose an LLM of a different size. Increase the temperature value.

During the ML development lifecycle, why does a data scientist perform exploratory data analysis (EDA) before building a model?. To monitor the model in production. To train the model. To deploy the model. To uncover the structure, quality, and relationships within the data.

In AI and Natural Language Processing (NLP), what is the term for the numerical representations of real-world objects and concepts that help models better understand text?. Embeddings. Tokens. Models. Parameters.

In generative AI, what are tokens?. The vector representations of words or concepts. The hidden layers of the neural network. The instructions or prompts given to the model. The basic units of input and output, such as words or subworkds.

A company uses Amazon SageMaker to deploy a model that detects whether social media posts contain certain topics. The company needs to show how different input features influence the model's behavior. Which SageMaker feature meets this requirement?. SegeMaker Featured Store. SageMaker Ground Truth. SageMaker Canvas. SageMaker Clarify.

An AI practitioner must improve the accuracy of a text-generation model that depends on rapidly changing inventory data. Which technique helps most?. Continues pre-training on inventory snapshots. Transfer learning. Fine-tune the model on historical inventory data. Retrieval Augmented Generation (RAG).

A financial institution trains ML models using data from multiple systems. Regulators require the institution to trace every piece of training data back to its source. Which practice meets this requirement?. Data Balancing. Data Argumentation. Data lineage tracking. Data normalization.

In a Retrieval Augmented Generation (RAG) workflow, what is the main purpose of chunking documents?. To avoid having to generate embeddings for the documents. To reduce the cost of storing the documents. To improve the relevance of passages retrieved from the vector index. To speed up training of the model.

A bank is building an AI application on Amazon Bedrock. The application sits in a VPC that, to satisfy regulators, must be cut off from all internet traffic. Which AWS service or feature meets these requirements?. Amazon Macie. Internal Gateway. AWS PrivateLink. Amazon Cloudfront.

A financial institution trains ML models using data from multiple internal systems. Regulators require the institution to trace every piece of training data back to its original source and demonstrate that the data was collected and processed in compliance with policy. Which practice meets this requirement?. Data Normalization. Data balancing. Data lineage tracking. Data argumentation.

A company generates long-form marketing content with a foundation model and wants to evaluate quality at scale without relying on human reviewers. Which evaluation approach uses another large language model to score the outputs?. BLEU Scoring. Benchmark dataset comparition. A/B testing with live users. LLM-as-a-judge.

Which technique can a company use to reduce bias and toxicity in a generative AI application during the postprocessing stage of the ML lifecycle?. Data augmentation. Feature engineering. Adversarial training. Human-in-the-loop.

An insurance company needs to run its ML model over several years of archived claims records to generate predictions, with each dataset running to several gigabytes. The results are not required immediately. Which Amazon SageMaker AI inference option best fits this need?. Serverless Interface. Real-time Interference. Batch transform. Asynchronos inference.

A team manages dozens of prompts across multiple generative AI applications and wants to track changes, compare variants, and revert to previous versions if quality drops. Which Amazon Bedrock feature meets this requirement?. Amazon Bedrock model evaluation. Amazon Bedrock Knowledge bases. Amazon Bedrock promt Management. Amazon Bedrock Guardrails.

A media company wants to use an AWS-developed foundation model to generate marketing copy and images. Which AWS service provides first-party foundation models built by Amazon?. Amazon Rekognition. Amazon Comprehend. Amazon Nova. Amazon Polly.