AI-102 Azure Study Guide
Posted in Azure, Azure Exams
In this blog post I cover all of the resources I came across whilst studying for the AZ-102 Exam
AI-102: AI Engineer on GitHub: – https://github.com/MicrosoftLearning/AI-102-AIEngineerhttps://github.com/MicrosoftLearning/AI-102-AIEngineer
And this too:-
https://microsoftlearning.github.io/AI-102-AIEngineer/
Plan and Manage an Azure Cognitive Services Solution (15-20%)
Select the appropriate Cognitive Services resource
- select the appropriate cognitive service for a vision solution
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/overview - select the appropriate cognitive service for a language analysis solution
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/what-is-luis - select the appropriate cognitive Service for a decision support solution
https://docs.microsoft.com/en-us/azure/cognitive-services/what-are-cognitive-services#decision-apis - select the appropriate cognitive service for a speech solution
https://docs.microsoft.com/en-us/azure/cognitive-services/what-are-cognitive-services#speech-apis
Plan and configure security for a Cognitive Services solution - manage Cognitive Services account keys
https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-apis-create-account?tabs=multiservice%2Cwindows#get-the-keys-for-your-resource - manage authentication for a resource
https://docs.microsoft.com/en-us/azure/cognitive-services/authentication?tabs=powershell - secure Cognitive Services by using Azure Virtual Network
https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-virtual-networks?tabs=portal - plan for a solution that meets responsible AI principles
https://www.microsoft.com/en-us/ai/responsible-ai-resources?activetab=pivot1%3aprimaryr4
Create a Cognitive Services resource - create a Cognitive Services resource
https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-apis-create-account?tabs=multiservice%2Cwindows - configure diagnostic logging for a Cognitive Services resource
https://docs.microsoft.com/en-us/azure/cognitive-services/diagnostic-logging - manage Cognitive Services costs
https://docs.microsoft.com/en-us/azure/cognitive-services/plan-manage-costs - monitor a cognitive service
https://docs.microsoft.com/en-us/azure/search/search-monitor-usage - implement a privacy policy in Cognitive Services
https://docs.microsoft.com/en-us/legal/cognitive-services/computer-vision/compliance-privacy-security-2
Plan and implement Cognitive Services containers - identify when to deploy to a container
https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-container-support - containerize Cognitive Services (including Computer Vision API, Face API, Text Analytics,
Speech, Form Recognizer)
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-container-howto?tabs=stt%2Ccsharp%2Csimple-format
Implement Computer Vision Solutions (20-25%)
Analyze images by using the Computer Vision API - retrieve image descriptions and tags by using the Computer Vision API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-tagging-images - identify landmarks and celebrities by using the Computer Vision API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-detecting-domain-content - detect brands in images by using the Computer Vision API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-brand-detection - moderate content in images by using the Computer Vision API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-detecting-adult-content - generate thumbnails by using the Computer Vision API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-generating-thumbnails
Extract text from images - extract text from images by using the OCR API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocr - extract text from images or PDFs by using the Read API
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocr#read-api - convert handwritten text by using Ink Recognizer
https://docs.microsoft.com/en-us/previous-versions/azure/cognitive-services/Ink-Recognizer/quickstarts/csharp - extract information from forms or receipts by using the pre-built receipt model in Form
Recognizer
https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/concept-receipts - build and optimize a custom model for Form Recognizer
https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/build-training-data-set
Extract facial information from images - detect faces in an image by using the Face API
https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/howtodetectfacesinimage - recognize faces in an image by using the Face API
https://docs.microsoft.com/en-us/azure/cognitive-services/face/quickstarts/client-libraries?tabs=visual-studio&pivots=programming-language-csharp
o configure persons and person groups
https://docs.microsoft.com/en-us/rest/api/cognitiveservices/face/persongroupperson/create - analyze facial attributes by using the Face API
https://docs.microsoft.com/en-in/learn/modules/detect-analyze-faces/2-face-analysis-azure - match similar faces by using the Face API
https://docs.microsoft.com/en-us/rest/api/faceapi/face/findsimilar
Implement image classification by using the Custom Vision service - label images by using the Computer Vision Portal
https://docs.microsoft.com/en-in/azure/cognitive-services/custom-vision-service/suggested-tags - train a custom image classification model in the Custom Vision Portal
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier - train a custom image classification model by using the SDK
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/quickstarts/image-classification?tabs=visual-studio&pivots=programming-language-csharp - manage model iterations
https://docs.microsoft.com/en-in/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier#manage-training-iterations - evaluate classification model metrics
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier#evaluate-the-classifier - publish a trained iteration of a model
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/use-prediction-api#publish-your-trained-iteration - export a model in an appropriate format for a specific target
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/export-your-model - consume a classification model from a client application
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-consume-web-service?tabs=python - deploy image classification custom models to containers
https://docs.microsoft.com/en-us/azure/iot-edge/tutorial-deploy-custom-vision?view=iotedge-2018-06
Implement an object detection solution by using the Custom Vision service - label images with bounding boxes by using the Computer Vision Portal
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-label-data#tag-images-and-specify-bounding-boxes-for-object-detection - train a custom object detection model by using the Custom Vision Portal
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector - train a custom object detection model by using the SDK
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/quickstarts/object-detection?tabs=visual-studio&pivots=programming-language-csharp - manage model iterations
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector#manage-training-iterations - evaluate object detection model metrics
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector#evaluate-the-detector - publish a trained iteration of a model
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/quickstarts/object-detection?tabs=visual-studio&pivots=programming-language-csharp#publish-the-current-iteration - consume an object detection model from a client application
https://docs.microsoft.com/en-us/ai-builder/object-detection-model-in-flow - deploy custom object detection models to containers
https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-container-support
Analyze video by using Video Indexer - process a video
https://docs.microsoft.com/en-us/azure/media-services/video-indexer/upload-index-videos - extract insights from a video
https://docs.microsoft.com/en-us/learn/modules/extract-insights-from-videos-with-video-indexer-service/ - moderate content in a video
https://azure.microsoft.com/en-gb/services/cognitive-services/content-moderator - customize the Brands model used by Video Indexer
https://docs.microsoft.com/en-us/azure/media-services/video-indexer/customize-brands-model-with-website - customize the Language model used by Video Indexer by using the Custom Speech
service
https://docs.microsoft.com/en-us/azure/media-services/video-indexer/customize-language-model-with-website - customize the Person model used by Video Indexer
https://docs.microsoft.com/en-us/azure/media-services/video-indexer/customize-person-model-with-website - extract insights from a live stream of video data
https://www.youtube.com/watch?v=wAHRBpqxpOg
Implement Natural Language Processing Solutions (20-25%)
Analyze text by using the Text Analytics service - retrieve and process key phrases
https://docs.microsoft.com/en-in/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-keyword-extraction - retrieve and process entity information (people, places, urls, etc.)
https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-entity-linking?tabs=version-3-preview - retrieve and process sentiment
https://docs.microsoft.com/en-us/azure/databricks/scenarios/databricks-sentiment-analysis-cognitive-services?toc=https%3A%2F%2Fdocs.microsoft.com%2Fen-us%2Fazure%2Fcognitive-services%2Ftext-analytics%2Ftoc.json&bc=https%3A%2F%2Fdocs.microsoft.com%2Fen-us%2Fazure%2Fbread%2Ftoc.json - detect the language used in text
https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-language-detection
Manage speech by using the Speech service - implement text-to-speech
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/text-to-speech - customize text-to-speech
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-voice - implement speech-to-text
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-speech-to-text?tabs=windowsinstall&pivots=programming-language-csharp - improve speech-to-text accuracy
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/tutorial-tenant-model
Translate language - translate text by using the Translator service
https://docs.microsoft.com/en-us/azure/cognitive-services/translator/translator-info-overview - translate speech-to-speech by using the Speech service
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-speech-translation?tabs=script%2Cwindowsinstall&pivots=programming-language-csharp - translate speech-to-text by using the Speech service
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-speech-to-text?tabs=windowsinstall&pivots=programming-language-csharp
Build an initial language model by using Language Understanding Service (LUIS) - create intents and entities based on a schema, and then add utterances
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-add-intents - create complex hierarchical entities
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-entity-types
o use this instead of roles
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-collaborate - train and deploy a model
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-train
Iterate on and optimize a language model by using LUIS - implement phrase lists
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-feature#create-a-phrase-list-for-a-concept - implement a model as a feature (i.e. prebuilt entities)
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-add-features#model-as-a-feature - manage punctuation and diacritics
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-reference-application-settings#punctuation-normalization - implement active learning
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-review-endpoint-utterances - monitor and correct data imbalances
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-use-dashboard#review-data-imbalance - implement patterns
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-tutorial-pattern
Manage a LUIS model - manage collaborators
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-collaborate - manage versioning
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-manage-versions - publish a model through the portal or in a container
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-publish-app - export a LUIS package
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-container-howto?tabs=v3#export-packaged-app-from-luis - deploy a LUIS package to a container
https://docs.microsoft.com/en-us/azure/cognitive-services/containers/azure-container-instance-recipe?tabs=portal - integrate Bot Framework (LUDown) to run outside of the LUIS portal
https://github.com/Microsoft/botbuilder-tools/tree/master/packages/Ludown#ludown
Implement Knowledge Mining Solutions (15-20%)
Implement a Cognitive Search solution - create data sources
https://docs.microsoft.com/en-us/rest/api/searchservice/create-data-source - define an index
https://docs.microsoft.com/en-us/azure/search/search-what-is-an-index - create and run an indexer
https://docs.microsoft.com/en-us/azure/search/search-howto-create-indexers#run-the-indexer - query an index
https://docs.microsoft.com/en-us/azure/search/search-query-overview - configure an index to support autocomplete and autosuggest
https://docs.microsoft.com/en-us/azure/search/search-add-autocomplete-suggestions - boost results based on relevance
https://docs.microsoft.com/en-us/azure/search/index-add-scoring-profiles - implement synonyms
https://docs.microsoft.com/en-us/azure/search/search-synonyms
Implement an enrichment pipeline - attach a Cognitive Services account to a skillset
https://docs.microsoft.com/en-us/azure/search/cognitive-search-attach-cognitive-services - select and include built-in skills for documents
https://docs.microsoft.com/en-us/azure/search/cognitive-search-predefined-skills - implement custom skills and include them in a skillset
https://docs.microsoft.com/en-us/azure/search/cognitive-search-custom-skill-interface
Implement a knowledge store - define file projections
https://docs.microsoft.com/en-us/azure/search/knowledge-store-projections-examples#projecting-to-file - define object projections
https://docs.microsoft.com/en-us/azure/search/knowledge-store-projections-examples#projecting-to-objects - define table projections
https://docs.microsoft.com/en-us/azure/search/knowledge-store-projections-examples#projecting-to-tables - query projections
https://docs.microsoft.com/en-us/azure/search/knowledge-store-projection-overview
Manage a Cognitive Search solution - provision Cognitive Search
https://docs.microsoft.com/en-us/azure/search/search-create-service-portal - configure security for Cognitive Search
https://docs.microsoft.com/en-us/azure/search/search-security-overview - configure scalability for Cognitive Search
https://docs.microsoft.com/en-us/azure/search/search-performance-optimization
Manage indexing - manage re-indexing
https://docs.microsoft.com/en-us/rest/api/searchservice/update-index - rebuild indexes
https://docs.microsoft.com/en-us/azure/search/search-howto-reindex - schedule indexing
https://docs.microsoft.com/en-us/azure/search/search-howto-schedule-indexers - monitor indexing
https://docs.microsoft.com/en-us/azure/search/search-howto-monitor-indexers - implement incremental indexing
https://docs.microsoft.com/en-us/azure/search/cognitive-search-incremental-indexing-conceptual - manage concurrency
https://docs.microsoft.com/en-us/azure/search/search-howto-concurrency - push data to an index
https://docs.microsoft.com/en-us/azure/search/search-what-is-data-import#pushing-data-to-an-index - troubleshoot indexing for a pipeline
https://docs.microsoft.com/en-us/azure/search/search-indexer-troubleshooting
Implement Conversational AI Solutions (15-20%)
Create a knowledge base by using QnA Maker - create a QnA Maker service
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/set-up-qnamaker-service-azure?tabs=v1#create-a-new-qna-maker-service - create a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/quickstarts/create-publish-knowledge-base?tabs=v1 - import a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/tutorials/migrate-knowledge-base#migrate-a-knowledge-base-from-qna-maker - train and test a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/quickstarts/create-publish-knowledge-base?tabs=v1#save-and-train - publish a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/quickstarts/create-publish-knowledge-base?tabs=v1#publish-the-knowledge-base - create a multi-turn conversation
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/multiturn-conversation - add alternate phrasing
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/edit-knowledge-base#add-alternate-questions - add chit-chat to a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/chit-chat-knowledge-base?tabs=v1 - export a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/tutorials/migrate-knowledge-base - add active learning to a knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/use-active-learning?tabs=v1 - manage collaborators
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/concepts/role-based-access-control
Design and implement conversation flow - design conversation logic for a bot
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-design-conversation-flow?view=azure-bot-service-4.0 - create and evaluate *.chat file conversations by using the Bot Framework Emulator
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-debug-transcript?view=azure-bot-service-4.0 - add language generation for a response
https://docs.microsoft.com/en-us/composer/concept-language-generation - design and implement adaptive cards
https://docs.microsoft.com/en-us/adaptive-cards/sdk/designer
Create a bot by using the Bot Framework SDK - implement dialogs
https://docs.microsoft.com/en-us/azure/bot-service/skill-actions-in-dialogs?view=azure-bot-service-4.0&tabs=cs - maintain state
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-concept-state?view=azure-bot-service-4.0 - implement logging for a bot conversation
https://docs.microsoft.com/en-us/azure/bot-service/using-trace-activities?view=azure-bot-service-4.0&tabs=csharp - implement a prompt for user input
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-primitive-prompts?view=azure-bot-service-4.0&tabs=csharp - add and review bot telemetry
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-telemetry?view=azure-bot-service-4.0&tabs=csharp - implement a bot-to-human handoff
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-design-pattern-handoff-human?view=azure-bot-service-4.0 - troubleshoot a conversational bot
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-troubleshoot-general-problems?view=azure-bot-service-4.0 - add a custom middleware for processing user messages
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-concept-middleware?view=azure-bot-service-4.0 - manage identity and authentication
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-authentication?view=azure-bot-service-4.0&tabs=aadv2%2Ccsharp - implement channel-specific logic
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-channeldata?view=azure-bot-service-4.0 - publish a bot
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial-deploy-basic-bot?view=azure-bot-service-4.0&tabs=csharp
Create a bot by using the Bot Framework Composer - implement dialogs
https://docs.microsoft.com/en-us/composer/concept-dialog - maintain state
https://docs.microsoft.com/en-us/composer/concept-memory - implement logging for a bot conversation
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-telemetry?view=azure-bot-service-4.0&tabs=csharp - implement prompts for user input
https://docs.microsoft.com/en-us/composer/how-to-ask-for-user-input - troubleshoot a conversational bot
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-troubleshoot-bot-configuration?view=azure-bot-service-4.0 - test a bot by using the Bot Framework Emulator
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-debug-emulator?view=azure-bot-service-4.0&tabs=csharp - publish a bot
https://docs.microsoft.com/en-us/composer/how-to-publish-bot
Integrate Cognitive Services into a bot - integrate a QnA Maker service
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-howto-qna?view=azure-bot-service-4.0&tabs=cs - integrate a LUIS service
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-howto-v4-luis?view=azure-bot-service-4.0&tabs=csharp - integrate a Speech service
https://docs.microsoft.com/en-us/azure/bot-service/rest-api/bot-framework-rest-connector-text-to-speech?view=azure-bot-service-4.0 - integrate Dispatch for multiple language models
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial-dispatch?view=azure-bot-service-4.0&tabs=cs - manage keys in app settings file
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-howto-v4-luis?view=azure-bot-service-4.0&tabs=csharp#update-the-settings-file
[…] AI-102 study guide by Gregor […]
[…] AI-102 study guide by Gregor […]
Hi GREGOR, it’s great post, thanks a lot. May I know that how long you take for this preparation? BR Louie
Hi Louie
I normally prepare for 1 month of an hour a night studying and trying things out in labs.