Valid AI-900 Dumps shared by PassLeader for Helping Passing AI-900 Exam! PassLeader now offer the newest AI-900 VCE dumps and AI-900 PDF dumps, the PassLeader AI-900 exam questions have been updated and ANSWERS have been corrected, get the newest PassLeader AI-900 dumps with VCE and PDF here: https://www.passleader.com/ai-900.html (374 Q&As Dumps)
BTW, DOWNLOAD part of PassLeader AI-900 dumps from Cloud Storage: https://drive.google.com/drive/folders/1_zzHedjSXrwFOpDLNo-2LpUDHqkC9z2B
NEW QUESTION 336
Which type of Azure AI workload should you use to create illustrations based on the text of an article?
A. natural language processing
B. generative AI
C. computer vision
D. Azure AI Document Intelligence
Answer: B
Explanation:
Azure generative AI, specifically through services like Azure AI Foundry, allows you to create illustrations based on text prompts using models like DALL-E. These models understand natural language descriptions and generate detailed, contextually accurate images.
https://create.microsoft.com/en-us/features/ai-image-generator
NEW QUESTION 337
Which Azure OpenAI model can be used to develop code?
A. microsoft-swinv2-base-patch4-window12-192-22k
B. Whisper
C. DALL-E
D. GPT-4-32k
Answer: D
Explanation:
The GPT-4 32k model can be used to develop programming code. It has a large context window, allowing it to process more information and generate more complex code. The model has shown strong performance in coding tasks, even surpassing its predecessor, o3-mini, in some domains.
https://vivekupadhyay1.medium.com/openai-chat-gpt-4-32k-detailed-document-ce3486e4786e
NEW QUESTION 338
You have an Azure subscription that uses Azure OpenAI. You need to create an original image of a rural scene to use on a website. What should you do?
A. From GitHub Copilot, provide instructions to create the image of the rural scene.
B. From Azure AI Foundry, deploy a GPT-3.5 Turbo model and provide instructions to create the image of the rural scene.
C. From Azure AI Foundry, deploy a DALL-E model, and provide instructions to create the rural scene.
D. From Microsoft Bing, search the term “rural scene” and download the results.
Answer: C
Explanation:
The image generation models generate images from text prompts that the user provides. GPT-image-1 is in limited access public preview. DALL-E 3 is generally available for use with the REST APIs. DALL-E 2 and DALL-E 3 with client SDKs are in preview.
https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models
NEW QUESTION 339
What are two common use cases for generative AI solutions? (Each correct answer presents a complete solution. Choose two.)
A. classifying email messages as spam or non-spam
B. generating draft responses for customer service agents
C. predicting sales revenue based on historical data
D. creating original artwork from textual descriptions
Answer: BD
Explanation:
– Option B: Generative AI tools can assist customer service agents by automatically drafting responses to customer inquiries, providing personalized and context-aware solutions. This helps agents improve efficiency, reduce workload, and enhance customer satisfaction.
– Option D: DALL·E 3, developed by OpenAI, is a cutting-edge generative AI model designed to create images from text descriptions.
https://medium.com/@eastgate/top-7-generative-ai-models-tools-for-text-image-and-video-creation-237a0de231b1
NEW QUESTION 340
You are creating an app to help employees write emails and reports based on user prompts. What should you use?
A. Azure AI Vision
B. Azure Machine Learning Studio
C. Azure OpenAI Service
D. Azure AI Speech
Answer: C
Explanation:
Azure OpenAI Service can generate text based on user prompts. It leverages GPT (Generative Pre-trained Transformer) models that are trained to understand and generate human-like text. Users interact with these models by providing a prompt, and the model attempts to produce the most likely continuation or completion of that text.
https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models
NEW QUESTION 341
What should you use to compare benchmark metrics of different AI models?
A. Azure Machine Learning Studio
B. the Azure AI Foundry Portal
C. Language Studio
D. Speech Studio
Answer: B
Explanation:
To compare benchmark metrics across Azure AI models, navigate to the Azure AI Foundry portal, explore the model catalog, and use the benchmarking tools to assess model performance. You can then compare these metrics to choose the most suitable model for your needs.
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/benchmark-model-in-catalog
NEW QUESTION 342
Which Azure OpenAI model should you use to summarize the text from a document?
A. Whisper
B. DALL-E
C. GPT
D. Codex
Answer: C
Explanation:
You can use ChatGPT to summarize text. This can help you understand complex information more easily, summarize the central argument of your own paper, or clarify your research question.
https://community.openai.com/t/information-summary-by-using-api/578792
NEW QUESTION 343
Verifying that machine learning models do NOT show racial or gender bias is an example of which Microsoft responsible AI principle?
A. fairness
B. privacy and security
C. safety
D. reliability
Answer: A
Explanation:
The fairness assessment component of the Responsible AI dashboard enables data scientists and developers to assess model fairness across sensitive groups defined in terms of gender, ethnicity, age, and other characteristics.
https://learn.microsoft.com/en-us/azure/machine-learning/concept-responsible-ai?view=azureml-api-2
NEW QUESTION 344
Stating the source of the data used to train a model is an example of which responsible AI principle?
A. transparency
B. privacy and security
C. fairness
D. reliability and safety
Answer: A
Explanation:
Transparency in AI refers to openly sharing information about how an AI system is designed, trained, and operates. Stating the source of the data used to train a model is an example of transparency, as it provides clarity about the origins of the data and helps stakeholders understand the model’s development process.
NEW QUESTION 345
What can be used to analyze scanned invoices and extract data, such as billing addresses and the total amount due?
A. Azure AI Custom Vision
B. Azure AI Search
C. Azure OpenAI
D. Azure AI Document Intelligence
Answer: D
Explanation:
The Document Intelligence invoice model uses powerful Optical Character Recognition (OCR) capabilities to analyze and extract key fields and line items from sales invoices, utility bills, and purchase orders.
https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/invoice
NEW QUESTION 346
In Azure Machine Learning, what are two ensemble methods for combining models in automated machine learning (automated ML)? (Each correct answer presents a complete solution. Choose two.)
A. voting
B. computer vision
C. stacking
D. classification
E. regression
Answer: AC
Explanation:
In Azure Machine Learning’s automated machine learning (AutoML), two prominent ensemble methods for combining models are Voting and Stacking.
https://learn.microsoft.com/en-us/azure/machine-learning/concept-automated-ml?view=azureml-api-2
NEW QUESTION 347
You have a dataset that contains experimental data for fuel samples. You need to predict the amount of energy in kilojoules that can be obtained from a sample based on its measured density. Which type of AI workload should you use?
A. Classification
B. Clustering
C. Knowledge Mining
D. Regression
Answer: D
Explanation:
Regression is a supervised machine learning technique which is used to predict continuous values. The ultimate goal of the regression algorithm is to plot a best-fit line or a curve between the data. The three main metrics that are used for evaluating the trained regression model are variance, bias and error.
https://builtin.com/data-science/regression-machine-learning
NEW QUESTION 348
You have a dataset that contains sales data and has defined labels for types of customers. You need to categorize the customer types based on the sales data. Which type of machine learning should you use?
A. Classification
B. Clustering
C. Regression
Answer: A
Explanation:
Classification is used with labeled data and is geared towards supervised learning, while clustering is used with unlabeled data, and geared towards unsupervised learning.
https://www.explorium.ai/blog/machine-learning/clustering-when-you-should-use-it-and-avoid-it
NEW QUESTION 349
You have an Azure Machine Learning model that generates a large quantity of false negatives. You need to reduce the number of false negatives without re-training the model. What should you do?
A. Use a different Machine Learning model.
B. Increase the amount of training data.
C. Adjust the threshold value.
D. Increase the number of training iterations.
Answer: C
Explanation:
One of the easiest methods to minimize the outcomes of a certain case is simply changing the decision boundary line from the basic 0.5 to above (when reducing False Positives) or below (when reducing False Negatives). It should be noted that by doing this, the possibility of False Positives increases. In other words, by decreasing the False Negatives we are increasing the False Positives.
https://www.kaggle.com/discussions/general/376229
NEW QUESTION 350
Which Azure Machine Learning capability should you use to quickly build and deploy a predictive model without extensive coding?
A. ML pipelines
B. Copilot
C. DALL-E
D. Automated machine learning (Automated ML)
Answer: D
Explanation:
To easily build and deploy a predictive model using Azure Machine Learning, start by selecting the appropriate tools for your task, such as Azure Machine Learning Studio or AutoML, and follow a streamlined process of data preparation, model training, and deployment. AutoML stands for Automated Machine Learning. It’s a process that automates the various tasks involved in building machine learning models, including data preparation, feature selection, model training, hyperparameter tuning, and model evaluation, according to IBM. This automation makes machine learning more accessible to a wider range of users, including those without extensive machine learning expertise.
https://learn.microsoft.com/en-us/azure/machine-learning/concept-automated-ml?view=azureml-api-2
NEW QUESTION 351
What should you use to identify similar faces in a set of images?
A. Azure AI Vision
B. Azure AI Custom Vision
C. Azure AI Language
D. Azure OpenAI Service
Answer: A
Explanation:
To identify similar faces across different images using Azure, the Azure AI Face service is the most suitable choice. This service leverages AI algorithms to detect, recognize, and analyze human faces, including features like face grouping based on visual similarity.
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/find-similar-faces
NEW QUESTION 352
Which action can be performed by using the Azure AI Vision service?
A. creating thumbnails for training videos
B. extracting data from handwritten letters
C. extracting key phrases from documents
D. identifying breeds of animals in live video streams
Answer: B
Explanation:
Azure AI Vision is a service within Azure Cognitive Services that enables developers to analyze visual data from images and videos. It includes OCR (Optical Character Recognition) capabilities, allowing you to extract text (both printed and handwritten) from images, PDFs, and scanned documents.
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-ocr
NEW QUESTION 353
What is the maximum image size that can be processed by using the prebuilt receipt model in Azure AI Document Intelligence?
A. 5 MB
B. 10 MB
C. 50 MB
D. 100 MB
Answer: C
Explanation:
For custom extraction model training, the total size of training data is 50 MB for template model and 1 GB for the neural model.
https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/id-document
NEW QUESTION 354
Capturing text from images is an example of which type of AI capability?
A. text analysis
B. optical character recognition (OCR)
C. image description
D. object detection
Answer: B
Explanation:
Optical Character Recognition (OCR) is a technology that converts images of text (like scanned documents or photos) into machine-readable, editable text. It’s used to extract text from various sources and make it accessible for digital editing, searching, and other manipulations.
https://www.ibm.com/think/topics/optical-character-recognition
NEW QUESTION 355
Which natural language processing feature can be used to identify the main talking points in customer feedback surveys?
A. language detection
B. translation
C. entity recognition
D. key phrase extraction
Answer: D
Explanation:
To identify main talking points in feedback using Azure natural language processing, the Key Phrase Extraction feature within the Azure AI Language service is the most appropriate choice. This feature analyzes text and extracts the most relevant and important phrases, effectively highlighting the core topics or themes present in the feedback.
https://learn.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing
NEW QUESTION 356
You are building a Conversational Language Understanding model for an e-commerce business. You need to ensure that the model detects when utterances are outside the intended scope of the model. What should you do?
A. Export the model.
B. Create a new model.
C. Add utterances to the None intent.
D. Create a prebuilt task entity.
Answer: C
Explanation:
The None intent is a required intent and can’t be deleted or renamed. The intent is meant to categorize utterances that don’t belong to any of your other custom intents. An utterance can be predicted as the None intent if the top scoring intent’s score is lower than the None score threshold.
https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/none-intent
NEW QUESTION 357
You need to identify harmful content in a generative AI solution that uses Azure OpenAI Service. What should you use?
A. Face
B. Video Analysis
C. Language
D. Content Safety
Answer: D
Explanation:
Azure AI Content Safety is a new Azure AI Service that can detect harmful user-generated and AI-generated content. This service is being integrated across MS products, including Azure OpenAI Service and Machine Learning prompt flow.
https://ivanatilca.medium.com/testing-azure-ai-content-safety-ccd512f9b350
NEW QUESTION 358
You deploy the Azure OpenAI service to generate images. You need to ensure that the service provides the highest level of protection against harmful content. What should you do?
A. Configure the Content filters settings.
B. Customize a large language model (LLM).
C. Configure the system prompt.
D. Change the model used by the Azure OpenAI service.
Answer: A
Explanation:
Azure OpenAI includes a content filtering system that works alongside core models, including image generation models. This system works by running both the prompt and completion through a set of classification models designed to detect and prevent the output of harmful content.
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter?view=foundry-classic
NEW QUESTION 359
You plan to create an AI application that will use Azure OpenAI Service. The solution requires that a specific amount of throughput be allocated. Which type of deployment should you use?
A. global batch
B. provisioned
C. data zone standard
D. standard
Answer: B
Explanation:
When a specific amount of throughput is needed with Azure OpenAI Service, you should use Provisioned Throughput Units (PTUs) for your deployment. PTUs allow you to reserve a fixed amount of processing capacity for your models, ensuring consistent performance and avoiding potential throttling or rate limits. In contrast, the “Standard” deployment option in Azure OpenAI Service uses a “pay-as-you-go” model, where you are billed for the amount of usage. While this can be suitable for applications with fluctuating usage patterns, it does not provide the same level of throughput control as PTUs. In summary: When you need to allocate a specific amount of throughput with Azure OpenAI Service, choose the “Provisioned” deployment type, which allows you to use PTUs.
https://github.com/MicrosoftDocs/azure-ai-docs/blob/main/articles/ai-services/openai/concepts/provisioned-throughput.md
NEW QUESTION 360
You plan to create an AI application that will read the license plates of motor vehicles by using Azure AI Foundry. The solution will be billed via tokens for inputs and outputs to the API. Which deployment option should you use?
A. Azure Kubernetes Service (AKS) cluster.
B. Azure virtual machines.
C. Serverless API.
D. Managed compute.
Answer: C
Explanation:
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/deployments-overview
NEW QUESTION 361
What should you use to identify similar faces in a set of images?
A. Azure OpenAI in Foundry Models
B. Azure AI Custom Vision
C. Azure AI Language
D. Azure AI Vision
Answer: D
Explanation:
To identify similar faces across different images using Azure, the Azure AI Face service is the most suitable choice. This service leverages AI algorithms to detect, recognize, and analyze human faces, including features like face grouping based on visual similarity.
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/find-similar-faces
NEW QUESTION 362
Which Azure AI Foundry Service can be used to identify documents that contain sensitive information?
A. Azure AI Document Intelligence
B. Azure AI Custom Vision
C. Azure AI Language
Answer: C
Explanation:
Azure AI Language can be used to identify documents containing sensitive information through its Personally Identifiable Information (PII) detection feature, which uses Named Entity Recognition (NER) to detect and categorize data like names, addresses, phone numbers, and financial details within unstructured text and native documents. This feature classifies sensitive data into predefined categories and can also redact the identified information, replacing it with asterisks to protect privacy.
https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/overview
NEW QUESTION 363
What should you use to explore pretrained generative AI models available from Microsoft and third-party providers?
A. Azure Machine Learning Designer
B. Azure Synapse Analytics
C. Azure AI Foundry
D. Language Studio
Answer: C
Explanation:
Azure AI Foundry Models gives you access to flagship models in Azure AI Foundry to consume them as APIs with flexible deployment options. Depending on what kind of project you’re using in Azure AI Foundry, you might see a different selection of these models. Specifically, if you’re using a Foundry project, built on an Azure AI Foundry resource, you see the models that are available for standard deployment to a Foundry resource. Alternatively, if you’re using a hub-based project, hosted by an Azure AI Foundry hub, you see models that are available for deployment to managed compute and serverless APIs. These model selections do overlap in many cases, since many models support the multiple deployment options.
https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models
NEW QUESTION 364
Which functionality in Azure AI Foundry enables you to test prompts for generative AI models?
A. evaluation
B. tracing
C. prompt flow
D. playgrounds
Answer: D
Explanation:
Azure AI Foundry playgrounds are designed for testing and prototyping prompts for generative AI models. You can use these interactive, web-based interfaces to experiment with various system and user prompts, compare different model responses in real-time, and even evaluate their performance using structured metrics like similarity and groundedness.
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/concept-playgrounds
NEW QUESTION 365
You are building a knowledge base by using Azure AI Language service’s custom answering feature. Which file format can you use to populate the knowledge base?
A. PPTX
B. PDF
C. JPEG
D. ZIP
Answer: B
Explanation:
Azure AI Language service’s custom answering can populate its knowledge base using various file formats, including structured text (.txt, .tsv), Microsoft Office documents (.docx, .xlsx, .pptx), and HTML, PDF, and Markdown files.
https://docs.azure.cn/en-us/ai-services/language-service/question-answering/reference/document-format-guidelines
NEW QUESTION 366
You plan to develop an AI application that will read the license plates of motor vehicles by using Azure AI Foundry. What should you use to develop the application?
A. Microsoft Visual Studio Code
B. GitHub Actions
C. Copilot for Microsoft 365
D. Azure AI Studio
Answer: D
Explanation:
Azure AI Studio (now Azure AI Foundry) is used to develop an AI application for reading license plates using its tools and models. The platform allows developers to build, customize, and deploy AI agents and applications, including those that process images to extract information like license plate numbers.
https://azure.microsoft.com/en-us/products/ai-foundry
NEW QUESTION 367
You are explaining generative AI workflows to a colleague. What is the first step of a generative AI workflow?
A. Deploy a generative AI model.
B. Fine-tune a model by using feedback.
C. Train a generative AI model by using data.
D. Generate outputs based on user prompts.
Answer: C
Explanation:
Training a generative AI model using data is a foundational step in the workflow, but it is preceded by data collection and preparation. After the model is trained, subsequent steps involve validation, generation, and refinement.
https://www.tricension.com/domainai/proper-training-for-generative-ai/
NEW QUESTION 368
HotSpot
You have the following apps:
– App1: Uses a set of images and photos to extract brand names.
– App2: Enables touchless access control for buildings.
Which Azure AI Vision service does each app use? (To answer, select the appropriate options in the answer area.)
Answer:
Explanation:
– Box 1: Optical character recognition (OCR). OCR technology can be used to extract brand names from images and photos by converting visible text into machine-readable text, which can then be used for various purposes like digital asset management, data entry, or content analysis. While basic OCR extracts text, advanced AI-powered OCR services can identify and categorize specific information like brand logos, colors, or objects within images, enabling more comprehensive analysis and understanding of image content.
– Box 2: Face. Azure AI Vision’s Face service can enable touchless access control for buildings by using facial recognition to identify authorized individuals and grant access, replacing or augmenting traditional methods like keycards. The service detects, recognizes, and analyzes faces in images to create a match from a database of approved facial templates. This offers enhanced security and a seamless experience for users entering a building.
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-ocr
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-identity
NEW QUESTION 369
Drag and Drop
Match the Azure AI service to the appropriate generative AI capability. To answer, drag the appropriate service from the column on the left to its capability on the right. Each service may be used once, more than once, or not at all.
Answer:
Explanation:
– Box 1: Azure AI Vision. To classify and label images, you would typically use Azure AI Vision, which is specifically designed for computer vision tasks. Azure AI Vision can perform image analysis, including classification, object detection, and generating captions. You can also use Azure AI Custom Vision to train custom models that are tailored to your specific needs.
– Box 2: Azure OpenAI Service. Azure OpenAI Service is designed to be used for generating conversational responses. It utilizes powerful language models like GPT-3.5 Turbo, GPT-4, and GPT-4o, which are specifically optimized for chat completion scenarios, according to Microsoft Learn. These models can handle multi-turn conversations and provide contextually appropriate responses based on user input, effectively simulating conversational AI behavior.
– Box 3: Azure AI Speech. The Speech service provides speech-to-text and text-to-speech capabilities with an Azure Speech resource. You can transcribe speech to text with high accuracy, produce natural-sounding text-to-speech voices, translate spoken audio, and use speaker recognition during conversations. Azure AI Speech service can be used for real-time speech-to-text conversion. It supports both real-time and batch transcription of audio streams into text. Real-time transcription allows for instant transcription of live audio inputs.
https://microsoftlearning.github.io/mslearn-ai-vision/Instructions/Exercises/02-image-classification.html
https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/overview
NEW QUESTION 370
……
Get the newest PassLeader AI-900 VCE dumps here: https://www.passleader.com/ai-900.html (374 Q&As Dumps)
And, DOWNLOAD the newest PassLeader AI-900 PDF dumps from Cloud Storage for free: https://drive.google.com/drive/folders/1_zzHedjSXrwFOpDLNo-2LpUDHqkC9z2B