Description
Candidates for Exam AI-102: Designing and Implementing a Microsoft Azure AI Solution build, manage, and deploy AI solutions that leverage Azure Cognitive Services and Azure Applied AI services. Their responsibilities include participating in all phases of AI solutions developmentβfrom requirements definition and design to development, deployment, maintenance, performance tuning, and monitoring. They work with solution architects to translate their vision and with data scientists, data engineers, IoT specialists, and AI developers to build complete end-to-end AI solutions. Candidates for this exam should be proficient in C# or Python and should be able to use REST-based APIs and SDKs to build computer vision, natural language processing, knowledge mining, and conversational AI solutions on Azure. They should also understand the components that make up the Azure AI portfolio and the available data storage options. Plus, candidates need to understand and be able to apply responsible AI principles. You may be eligible for ACE college credit if you pass this certification exam. See ACE college credit for certification exams for details. Languages: English, Japanese, Chinese (Simplified), Korean, German, French, Spanish, Portuguese (Brazil), Arabic (Saudi Arabia), Russian, Chinese (Traditional), Italian, Indonesian (Indonesia) Retirement date: none This exam measures your ability to accomplish the following technical tasks: plan and manage an Azure Cognitive Services solutions; implement Computer Vision solutions; implement natural language processing solutions; implement knowledge mining solutions; and implement conversational AI solutions. This Training Covers The English language version of this exam was updated on October 25, 2022. Download the study guide in the preceding βTipβ box for more details about the skills measured on this exam. Plan and manage an Azure Cognitive Services solution (10β15%) Implement Computer Vision solutions (20β25%) Implement natural language processing solutions (25β30%) Implement knowledge mining solutions (15β20%) Implement conversational AI solutions (10β15%) This study guide should help you understand what to expect on the exam and includes a summary of the topics the exam might cover and links to additional resources. The information and materials in this document should help you focus your studies as you prepare for the exam. Useful links Description How to earn the certification Some certifications only require one exam, while others require more. On the details page, youβll find information about what skills are measured and links to registration. Each exam also has its own details page covering exam specifics. Certification renewal Once you earn your certification, donβt let it expire. When you have an active certification thatβs expiring within six months, you should renew itβat no costβby passing a renewal assessment on Microsoft Learn. Remember to renew your certification annually if you want to retain it. Your Microsoft Learn profile Connecting your certification profile to Learn brings all your learning activities together. Youβll be able to schedule and renew exams, share and print certificates, badges and transcripts, and review your learning statistics inside your Learn profile. Passing score All technical exam scores are reported on a scale of 1 to 1,000. A passing score is 700 or greater. As this is a scaled score, it may not equal 70% of the points. A passing score is based on the knowledge and skills needed to demonstrate competence as well as the difficulty of the questions. Exam sandbox Are you new to Microsoft certification exams? You can explore the exam environment by visiting our exam sandbox. We created the sandbox as an opportunity for you to experience an exam before you take it. In the sandbox, Useful links Description you can interact with different question types, such as build list, case studies, and others that you might encounter in the user interface when you take an exam. Additionally, it includes the introductory screens, instructions, and help topics related to the different types of questions that your exam might include. It also includes the non-disclosure agreement that you must accept before you can launch the exam. Request accommodations Weβre committed to ensuring all learners are set up for success. If you use assistive devices, require extra time, or need modification to any part of the exam experience, you can request an accommodation. Take a practice test Taking a practice test is a great way to know whether youβre ready to take the exam or if you need to study a bit more. Subject-matter experts write the Microsoft Official Practice Tests, which are designed to assess all exam objectives. Objective domain: skills the exam measures The English language version of this exam was updated on October 25, 2022. Some exams are localized into other languages, and those are updated approximately eight weeks after the English version is updated. Other available languages are listed in the Schedule Exam section of the Exam Details webpage. If the exam isnβt available in your preferred language, you can request an additional 30 minutes to complete the exam. Note The bullets that follow each of the skills measured are intended to illustrate how we are assessing that skill. Related topics may be covered in the exam. Note Most questions cover features that are general availability (GA). The exam may contain questions on Preview features if those features are commonly used. Functional groups Plan and manage an Azure Cognitive Services solution (10β15%) Select the appropriate Cognitive Services resource β’ Select the appropriate cognitive service for a vision solution β’ Select the appropriate cognitive service for a language analysis solution β’ Select the appropriate cognitive Service for a decision support solution β’ Select the appropriate cognitive service for a speech solution Plan and configure security for a Cognitive Services solution β’ Manage Cognitive Services account keys β’ Manage authentication for a resource β’ Secure Cognitive Services by using Azure Virtual Network β’ Plan for a solution that meets responsible AI principles Create a Cognitive Services resource β’ Create a Cognitive Services resource β’ Configure diagnostic logging for a Cognitive Services resource β’ Manage Cognitive Services costs β’ Monitor a Cognitive Services resource β’ Implement a privacy policy in Cognitive Services Plan and implement Cognitive Services containers β’ Identify when to deploy to a container β’ Containerize Cognitive Services (including Computer Vision, Language, Speech, Form Recognizer) β’ Deploy Cognitive Services containers in Microsoft Azure Implement Computer Vision solutions (20β25%) Analyze images by using the Computer Vision API β’ Retrieve image descriptions and tags by using the Computer Vision API β’ Identify landmarks by using the Computer Vision API β’ Detect brands in images by using the Computer Vision API β’ Moderate content in images by using the Computer Vision API β’ Generate thumbnails by using the Computer Vision API Extract text from images β’ Extract text from images or PDFs by using the Computer Vision service β’ Extract information using pre-built models in Form Recognizer β’ Build and optimize a custom model for Form Recognizer Extract facial information from images β’ Detect faces in an image by using the Face API β’ Recognize faces in an image by using the Face API β’ Match similar faces by using the Face API Implement image classification by using the Custom Vision service β’ Label images by using the Custom Vision Portal β’ Train a custom image classification model in the Custom Vision Portal β’ Train a custom image classification model by using the SDK β’ Manage model iterations β’ Evaluate classification model metrics β’ Publish a trained iteration of a model β’ Export a model in an appropriate format for a specific target β’ Consume a classification model from a client application β’ Deploy image classification custom models to containers Implement an object detection solution by using the Custom Vision service β’ Label images with bounding boxes by using the Custom Vision Portal β’ Train a custom object detection model by using the Custom Vision Portal β’ Train a custom object detection model by using the SDK β’ Manage model iterations β’ Evaluate object detection model metrics β’ Publish a trained iteration of a model β’ Consume an object detection model from a client application β’ Deploy custom object detection models to containers Analyze video by using Azure Video Analyzer for Media (formerly Video Indexer) β’ Process a video β’ Extract insights from a video β’ Moderate content in a video β’ Customize the Brands model used by Video Analyzer for Media β’ Customize the Language model used by Video Analyzer for Media by using the Custom Speech service β’ Extract insights from a live stream of video data Implement natural language processing solutions (25β30%) Analyze text by using the Language service β’ Retrieve and process key phrases β’ Retrieve and process entity information (people, places, URLs, etc.) β’ Retrieve and process sentiment β’ Detect the language used in text Manage speech by using the Speech service β’ Implement text-to-speech β’ Customize text-to-speech β’ Implement speech-to-text β’ Improve speech-to-text accuracy β’ Improve text-to-speech accuracy β’ Implement intent recognition Translate language β’ Translate text by using the Translator service β’ Translate speech-to-speech by using the Speech service β’ Translate speech-to-text by using the Speech service Build an initial language model by using language understanding β’ Create intents and entities based on a schema, and add utterances β’ Create complex hierarchical entities β’ Train and deploy a model Iterate on and optimize a language model by using language understanding β’ Implement phrase lists β’ Implement a model as a feature (i.e., prebuilt entities) β’ Manage punctuation and diacritics β’ Implement active learning β’ Monitor and correct data imbalances β’ Implement patterns Manage a language understanding model β’ Manage collaborators β’ Manage versioning β’ Publish a model through the portal or in a container β’ Export a Language Service package β’ Deploy a Language Service package to a container Create a Questions Answering solution using the Language service β’ Create a question answering project β’ Import questions and answers β’ Train and test a knowledge base β’ Publish a knowledge base β’ Create a multi-turn conversation β’ Add alternate phrasing β’ Add chit-chat to a knowledge base β’ Export a knowledge base β’ Add active learning to a knowledge base Implement knowledge mining solutions (15β20%) Implement a Cognitive Search solution β’ Create data sources β’ Define an index β’ Create and run an indexer β’ Query an index β’ Configure an index to support autocomplete and autosuggest β’ Boost results based on relevance β’ Implement synonyms Implement an AI enrichment pipeline β’ Attach a Cognitive Services account to a skillset β’ Select and include built-in skills for documents β’ Implement custom skills and include them in a skillset Implement a knowledge store β’ Define file projections β’ Define object projections β’ Define table projections β’ Query projections Manage a Cognitive Search solution β’ Provision Cognitive Search β’ Configure security for Cognitive Search β’ Configure scalability for Cognitive Search Manage indexing β’ Manage re-indexing β’ Rebuild indexes β’ Schedule indexing β’ Monitor indexing β’ Implement incremental indexing β’ Manage concurrency β’ Push data to an index β’ Troubleshoot indexing for a pipeline Implement conversational AI solutions (10β15%) Design and implement conversation flow β’ Design conversational logic for a bot β’ Create and evaluate .chat file conversations by using the Bot Framework Emulator β’ Choose an appropriate conversational model for a bot, including activity handlers and dialogs Create a bot by using the Bot Framework SDK β’ Use the Bot Framework SDK to create a bot from a template β’ Implement activity handlers and dialogs β’ Use a turn context β’ Test a bot using the Bot Framework Emulator β’ Deploy a bot to Azure Create a bot by using the Bot Framework Composer β’ Implement dialogs β’ Maintain state β’ Implement logging for a bot conversation β’ Implement prompts for user input β’ Troubleshoot a conversational bot β’ Test a bot β’ Publish a bot β’ Add language generation for a response β’ Design and implement Adaptive Cards Integrate Cognitive Services into a bot β’ Integrate a question answering model β’ Integrate a language understanding service β’ Integrate a Speech service resource Sample Questions QUESTION 1 You are developing the smart e-commerce project. You need to implement autocompletion as part of the Cognitive Search solution. Which three actions should you perform? Each correct answer presents part of the solution. (Choose three.) NOTE: Each correct selection is worth one point. A. Make API queries to the autocomplete endpoint and include suggesterName in the body. B. Add a suggester that has the three product name fields as source fields. C. Make API queries to the search endpoint and include the product name fields in the searchFields query parameter. D. Add a suggester for each of the three product name fields. E. Set the searchAnalyzer property for the three product name variants. F. Set the analyzer property for the three product name variants. Answer: A,B,F Explanation: Scenario: Support autocompletion and autosuggestion based on all product name variants. A: Call a suggester-enabled query, in the form of a Suggestion request or Autocomplete request, using an API. API usage is illustrated in the following call to the Autocomplete REST API. POST /indexes/myxboxgames/docs/autocomplete?search&api-version=2020-06-30 { “search”: “minecraf”, “suggesterName”: “sg” } B: In Azure Cognitive Search, typeahead or “search-as-you-type” is enabled through a suggester. A suggester provides a list of fields that undergo additional tokenization, generating prefix sequences to support matches on partial terms. For example, a suggester that includes a City field with a value for “Seattle” will have prefix combinations of “sea”, “seat”, “seatt”, and “seattl” to support typeahead. F. Use the default standard Lucene analyzer (“analyzer”: null) or a language analyzer (for example, “analyzer”: “en.Microsoft”) on the field. QUESTION 2 You are developing the chatbot. You create the following components: β’ A QnA Maker resource β’ A chatbot by using the Azure Bot Framework SDK You need to add an additional component to meet the technical requirements and the chatbot requirements. What should you add? A. Dispatch B. chatdown C. Language Understanding D. Microsoft Translator Answer: A Explanation: Scenario: All planned projects must support English, French, and Portuguese. If a bot uses multiple LUIS models and QnA Maker knowledge bases (knowledge bases), you can use the Dispatch tool to determine which LUIS model or QnA Maker knowledge base best matches the user input. The dispatch tool does this by creating a single LUIS app to route user input to the correct model. QUESTION 3 You are developing the document processing workflow. You need to identify which API endpoints to use to extract text from the financial documents. The solution must meet the document processing requirements. Which two API endpoints should you identify? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point. A. /vision/v3.2/read/analyzeResults B. /formrecognizer/v2.0/prebuilt/receipt/analyze C. /vision/v3.2/read/analyze D. /vision/v3.2/describe E. /formercognizer/v2.0/custom/models{modelId}/ analyze Answer: B,C Explanation: C: Analyze Receipt – Get Analyze Receipt Result. Query the status and retrieve the result of an Analyze Receipt operation. Request URL: Error! Hyperlink reference not valid. E: POST {Endpoint}/vision/v3.2/read/analyze Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents. Scenario: Contoso plans to develop a document processing workflow to extract information automatically from PDFs and images of financial documents The document processing solution must be able to process standardized financial documents that have the following characteristics: – Contain fewer than 20 pages. – Be formatted as PDF or JPEG files. – Have a distinct standard for each office. *The document processing solution must be able to extract tables and text from the financial documents. The document processing solution must be able to extract information from receipt images. QUESTION 4 You are developing the chatbot. You create the following components: * A QnA Maker resource * A chatbot by using the Azure Bot Framework SDK. You need to integrate the components to meet the chatbot requirements. Which property should you use? A. QnADialogResponseOptions.CardNoMatchText B. Qna MakerOptions-ScoreThreshold C. Qna Maker Op t ions StrickFilters D. QnaMakerOptions.RankerType Answer: D Explanation: Scenario: When the response confidence score is low, ensure that the chatbot can provide other response options to the customers. When no good match is found by the ranker, the confidence score of 0.0 or “None” is returned and the default response is “No good match found in the KB”. You can override this default response in the bot or application code calling the endpoint. Alternately, you can also set the override response in Azure and this changes the default for all knowledge bases deployed in a particular QnA Maker service. Choosing Ranker type: By default, QnA Maker searches through questions and answers. If you want to search through questions only, to generate an answer, use the RankerType=QuestionOnly in the POST body of the GenerateAnswer request. QUESTION 5 You are developing the knowledgebase. You use Azure Video Analyzer for Media (previously Video indexer) to obtain transcripts of webinars. You need to ensure that the solution meets the knowledgebase requirements. What should you do? A. Create a custom language model B. Configure audio indexing for videos only C. Enable multi-language detection for videos D. Build a custom Person model for webinar presenters Answer: B Explanation: Can search content in different formats, including video Audio and video insights (multi-channels). When indexing by one channel, partial result for those models will be available. Keywords extraction: Extracts keywords from speech and visual text. Named entities extraction: Extracts brands, locations, and people from speech and visual text via natural language processing (NLP). Topic inference: Makes inference of main topics from transcripts. The 2nd-level IPTC taxonomy is included. Artifacts: Extracts rich set of “next level of details” artifacts for each of the models. Sentiment analysis: Identifies positive, negative, and neutral sentiments from speech and visual text. QUESTION 6 You are developing the knowledgebase by using Azure Cognitive Search. You need to process wiki content to meet the technical requirements. What should you include in the solution? A. an indexer for Azure Blob storage attached to a skillset that contains the language detection skill and the text translation skill B. an indexer for Azure Blob storage attached to a skillset that contains the language detection skill C. an indexer for Azure Cosmos DB attached to a skillset that contains the document extraction skill and the text translation skill D. an indexer for Azure Cosmos DB attached to a skillset that contains the language detection skill and the text translation skill Answer: C Explanation: The wiki contains text in English, French and Portuguese. Scenario: All planned projects must support English, French, and Portuguese. The Document Extraction skill extracts content from a file within the enrichment pipeline. This allows you to take advantage of the document extraction step that normally happens before the skillset execution with files that may be generated by other skills. Note: The Translator Text API will be used to determine the from language. The Language detection skill is not required. Students Feed Back Jsaon I always enjoy Scott Duffy training videos. I like how this followed the skills outline from Microsoft. It was a great course which helped me to clear AI-102, I had previous experience in QnA Maker and Bot services but other major areas are very well covered by Scott. In the practice test I scored 70% in the first attempt.. but it gave proper understanding and logic building thrust. Jessica This course is a great walkthrough Azure Cognitive Services, but definitely not prep material for AI-102 exam. Scott: cleard my exam in one week Despite being recently updated this course feels out of date, for example there are 31 minutes of videos on QnA maker, but this service does not appear on the current study guide and its not clear from the course content how this differs from its replacement (Azure Cognitive Service for Language). Furthermore, 10 minutes of videos on knowledge mining feels low for an area that makes up 15-20% of the exam Richel I have cleared exam today with 900!, these mock tests were very helpful to me and highly recommended. Thank you David Successfully cleared AI-102 exam today with 960 marks. All the questions similar and came from this Mock tests. Thanks a lot Joogate. Make The Best Choice Chose – Joogate Make yourself more valuable in today’s competitive computer industry Joogate’s preparation material includes the most excellent features, prepared by the same dedicated experts who have come together to offer an integrated solution. We provide the most excellent and simple method to pass your Microsoft Microsoft Certified: Azure AI Engineer Associate AI-102 exam on the first attempt . will prepare you for your exam effectively. AI-102 Study Guide. Your exam will download as a single AI-102 PDF or complete AI-102 preparation material as well as over +4000 other technical exam PDF and study material downloads. Forget buying your prep materials separately at three time the price of our – skip the AI-102 audio exams and select the one package that gives it all to you at your discretion: AI-102 Study Materials featuring the study material. Joogate AI-102 Exam Prepration Tools Joogate Microsoft Microsoft Certified: Azure AI Engineer Associate preparation begins and ends with your accomplishing this credential goal. Although you will take each Microsoft Microsoft Certified: Azure AI Engineer Associate online test one at a time – each one builds upon the previous. Remember that each Microsoft Microsoft Certified: Azure AI Engineer Associate exam paper is built from a common certification foundation. AI-102 Exam preparation materials Beyond knowing the answer, and actually understanding the AI-102 test questions puts you one step ahead of the test. Completely understanding a concept and reasoning behind how something works, makes your task second nature. Your AI-102 quiz will melt in your hands if you know the logic behind the concepts. Any legitimate Microsoft Microsoft Certified: Azure AI Engineer Associate prep materials should enforce this style of learning – but you will be hard pressed to find more than a Microsoft Microsoft Certified: Azure AI Engineer Associate practice test anywhere other than Joogate. AI-102 Exam Questions and Answers with Explanation This is where your Microsoft Microsoft Certified: Azure AI Engineer Associate AI-102 exam prep really takes off, in the testing your knowledge and ability to quickly come up with answers in the AI-102 online tests. Using Microsoft Certified: Azure AI Engineer Associate AI-102 practice exams is an excellent way to increase response time and queue certain answers to common issues. AI-102 Exam Study Guides All Microsoft Microsoft Certified: Azure AI Engineer Associate online tests begin somewhere, and that is what the Microsoft Microsoft Certified: Azure AI Engineer Associate training course will do for you: create a foundation to build on. Study guides are essentially a detailed Microsoft Microsoft Certified: Azure AI Engineer Associate AI-102 tutorial and are great introductions to new Microsoft Microsoft Certified: Azure AI Engineer Associate training courses as you advance. The content is always relevant, and compound again to make you pass your AI-102 exams on the first attempt. You will frequently find these AI-102 PDF files downloadable and can then archive or print them for extra reading or studying on-the-go. AI-102 Exam Video Training For some, this is the best way to get the latest Microsoft Microsoft Certified: Azure AI Engineer Associate AI-102 training. However you decide to learn AI-102 exam topics is up to you and your learning style. The Joogate Microsoft Microsoft Certified: Azure AI Engineer Associate products and tools are designed to work well with every learning style. Give us a try and sample our work. You’ll be glad you did. AI-102 Other Features * Realistic practice questions just like the ones found on certification exams. * Each guide is composed from industry leading professionals real Microsoft Microsoft Certified: Azure AI Engineer Associatenotes, certifying 100% brain dump free. * Study guides and exam papers are help you prepare effectively or . * Designed to help you complete your certificate using only * Delivered in PDF format for easy reading and printing Joogate unique CBT AI-102 will have you dancing the Microsoft Microsoft Certified: Azure AI Engineer Associate jig before you know it * Microsoft Certified: Azure AI Engineer Associate AI-102 prep files are frequently updated to maintain accuracy. Your courses will always be up to date. Get Microsoft Certified: Azure AI Engineer Associate ebooks from Joogate which contain real AI-102 exam questions and answers. You WILL pass your Microsoft Certified: Azure AI Engineer Associate exam on the first attempt using only Joogate’s Microsoft Certified: Azure AI Engineer Associate excellent preparation tools and tutorials.
Reviews
There are no reviews yet.