FYI - I passed this exam on my first attempt - score was 970, passmark was 700
A Repository created to help people prepare for the Microsoft AI-900 Exam. Details are correct for December 2020, as I prepare for an exam in January 2021 - I make no promises for the lifecycle of this repository at this time.
Also, I'd love it if you've found this Project useful - Could you please click on the ⭐ for this repository.
If you have content to add, open an issue and we'll see if it fits
- Exam Rubric/Scoring Guide
- Learning Paths
- Describe Artificial Intelligence workloads and considerations (15-20%)
- Describe fundamental principles of machine learning on Azure (30-35%)
- Describe features of computer vision workloads on Azure (15-20%)
- Describe features of Natural Language Processing (NLP) workloads on Azure (15-20%)
Microsoft Azure AI Fundamentals – Skills Measured
| Resource | Topic | Step |
|---|---|---|
| Get started with artificial intelligence on Azure | Topic | Artificial Intelligence (AI) empowers amazing new solutions and experiences; and Microsoft Azure provides easy to use services to help you get started |
| Create no-code predictive models with Azure Machine Learning | Topic | Machine learning is at the core of artificial intelligence, and many modern applications and services depend on predictive machine learning models. Learn how to use Azure Machine Learning to create and publish models without writing code |
| Explore computer vision in Microsoft Azure | Topic | Computer vision is an area of artificial intelligence (AI) in which software systems are designed to perceive the world visually, though cameras, images, and video. There are multiple specific types of computer vision problem that AI engineers and data scientists can solve using a mix of custom machine learning models and platform-as-a-service (PaaS) solutions - including many cognitive services in Microsoft Azure |
| Explore natural language processing | Topic | Natural language processing supports applications that can see, hear, speak with, and understand users. Using text analytics, translation, and language understanding services, Microsoft Azure makes it easy to build applications that support natural language |
| Explore conversational AI | Topic | Conversational AI is an artificial intelligence workload that deals with dialogs between AI agents and human users |
Click here for My Notes on AI Workloads
| Resource | Topic | Notes |
|---|---|---|
| Overview of the prediction model | Identify features of common AI workloads | Notes |
| What is the Text Analytics API? | Identify features of common AI workloads | Notes |
| How bots work | Identify features of common AI workloads | Notes |
| What is Computer Vision? | Identify features of common AI workloads | Notes |
| How to: Sentiment analysis and Opinion Mining | Identify features of common AI workloads | Notes |
| Use QnA Maker to answer questions | Identify features of common AI workloads | Notes |
| Example: How to extract key phrases using Text Analytics | Identify features of common AI workloads | Notes |
| What is the Anomaly Detector API? | Identify features of common AI workloads | Notes |
| Knowledge mining | Identify features of common AI workloads | Notes |
| Analyze videos in near real time | Identify features of common AI workloads | Notes |
| What is the Speech service? | Identify features of common AI workloads | Notes |
| How to: Use the Anomaly Detector API on your time series data | Identify features of common AI workloads | Notes |
| Artificial intelligence (AI) | Identify features of common AI workloads | Notes |
| To Go the Distance, We Built Systems That Could Better Perceive It | Identify features of common AI workloads | Notes |
| Anomaly Detector | Identify features of common AI workloads | Notes |
| Introducing Azure Anomaly Detector API | Identify features of common AI workloads | Notes |
| What is Azure Machine Learning? | Identify features of common AI workloads | Notes |
| Understand computer vision | Identify features of common AI workloads | Notes |
| Understand natural language processing | Identify features of common AI workloads | Notes |
| Understand conversational AI | Identify features of common AI workloads | Notes |
| Understand anomaly detection | Identify features of common AI workloads | Notes |
| Understand machine learning | Identify features of common AI workloads | Notes |
| Implement knowledge mining with Azure Cognitive Search | Identify features of common AI workloads | Notes |
| Responsible AI resources | Identify guiding principles for responsible AI | Notes |
| Responsible AI | Identify guiding principles for responsible AI | Notes |
| Guiding principles of our identity strategy: staying ahead of evolving customer needs | Identify guiding principles for responsible AI | Notes |
| Understand responsible AI | Identify guiding principles for responsible AI | Notes |
Click here for My Notes on AI Principles
Click here for My Notes on Computer Vision
| Resource | Topic | Step |
|---|---|---|
| What is Computer Vision? | Topic | Step |
| Detect common objects in images | Topic | Bounding box coordinates for all identified objects, animals etc |
| SEMANTIC SEGMENTATION AS IMAGE REPRESENTATION FOR SCENE RECOGNITION | Topic | Pixel-level classification of an image |
| Optical Character Recognition (OCR) | Topic | Retrieval of printed text from a scanned document |
| Face detection with Computer Vision | Topic | Identify human faces, generate a rectangle for each detected face, provide details such as age, gender or emotion |
| Intro to classification of images | Topic | Step |
| Get started with image classification on Azure | Topic | Step |
| Get started with object detection on Azure | Topic | Step |
| Get started with OCR on Azure | Topic | Step |
| An overview of semantic image segmentation | Topic | Which pixels belong to which object. Used when an AI system needs to understand the context in which it operates, for example, a self-driving car |
| Get started with object detection on Azure | Topic | Identifies and tags individual features(objects) in a model. Return the coordinates of a box surrounding a tagged visual feature. |
| Computer Vision 86-category taxonomy | Topic | Step |
| Detect color schemes in images | Topic | Detecting colour scheme is an example of image classification |
| Get started with Face analysis on Azure | Topic | Step |
| Face detection and attributes | Topic | Step |
| Face detection with Computer Vision | Topic | Step |
| Specify a face detection model | Topic | Step |
| Face mask detection with Azure Cognitive services Custom Vision | Topic | Step |
| What is the Azure Face service? | Topic | Step |
| How to use Named Entity Recognition in Text Analytics | Topic | Step |
| What is the Anomaly Detector API? | Topic | Step |
| What is Speaker Recognition (Preview)? | Topic | “who is speaking?” |
| Query the knowledge base for answers | Topic | Step |
| Detect adult content | Topic | Computer Vision can detect adult material in images so that developers can restrict the display of these images in their software. Content flags are applied with a score between zero and one so developers can interpret the results according to their own preferences |
| What is the Translator service? | Topic | Translator is a cloud-based machine translation service and is part of the Azure Cognitive Services family of cognitive APIs used to build intelligent apps. Translator is easy to integrate in your applications, websites, tools, and solutions. It allows you to add multi-language user experiences in more than 70 languages, and can be used on any hardware platform with any operating system for text translation |
| What is Custom Vision? | Topic | Step |
| Module: K-Means Clustering | Topic | Step |
| What is Azure Media Services Video Indexer? | Topic | Step |
| Face recognition concepts | Topic | Step |
| What are the Bing Search APIs? | Topic | Step |
| What is the Bing Visual Search API? | Topic | Recipes, where to buy, similar |
| Images - Visual Search | Topic | Visual Search API lets you discover insights about an image such as visually similar images, shopping sources, and related searches. The API can also perform text recognition, identify entities (people, places, things), return other topical content for the user to explore, and more |
| What is the Text Analytics API? | Azure Cognitive Services | The Text Analytics API is a cloud-based service that provides Natural Language Processing (NLP) features for text mining and text analysis, including: sentiment analysis, opinion mining, key phrase extraction, language detection, and named entity recognition |
| What is Form Recognizer? | Topic | extract text, selection marks, and table structure (the row and column numbers associated with the text) using high-definition optical character recognition (OCR) |
| Receipt concepts | Topic | Azure Form Recognizer can analyze receipts using one of its prebuilt models. The Receipt API extracts key information from sales receipts in English, such as merchant name, transaction date, transaction total, line items, and more |
| What is Personalizer? | Topic | choose the best content item to show your users |
| What is Azure Media Services Video Indexer? | Azure Cognitive Services | Get deep insights into large video archives through multi-channel (audio and video) analysis. |
| What is the Bing Image Search API? | Topic | By sending search queries to the API, you can get high-quality images |
| Business card concepts | Topic | The Business Card API combines powerful Optical Character Recognition (OCR) capabilities with our Business Card Understanding model to extract key information from business cards in English |
| Receipt concepts | Topic | The Receipt API extracts key information from sales receipts in English, such as merchant name, transaction date, transaction total, line items, and more. |
| Train a Form Recognizer model with labels using the sample labeling tool | Topic | Step |
| What's new in Form Recognizer? | Topic | New languages supported In addition to English, the following languages are now supported: for Layout and Train Custom Model: English (en), Chinese (Simplified) (zh-Hans), Dutch (nl), French (fr), German (de), Italian (it), Portuguese (pt) and Spanish (es) |
| Use the HeadPose attribute | Topic | Step |
| What is Language Understanding (LUIS)? | Topic | Language Understanding (LUIS) is a cloud-based conversational AI service that applies custom machine-learning intelligence to a user's conversational, natural language text to predict overall meaning, and pull out relevant, detailed information |
Click here for My Notes on NLP workloads
| Resource | Topic | Step |
|---|---|---|
| Example: How to extract key phrases using Text Analytics | Topic | The Key Phrase Extraction API evaluates unstructured text, and for each JSON document, returns a list of key phrases |
| What is text-to-speech? | Topic | convert text into human-like synthesized speech |
| Improve synthesis with Speech Synthesis Markup Language (SSML) | Topic | XML-based markup language that lets developers specify how input text is converted into synthesized speech using the text-to-speech service. Compared to plain text, SSML allows developers to fine-tune the pitch, pronunciation, speaking rate, volume, and more of the text-to-speech output |
| How to use Named Entity Recognition in Text Analytics | Topic | Step |
| How to: Sentiment analysis and Opinion Mining | Topic | If you send a Sentiment Analysis request, the API will return sentiment labels (such as "negative", "neutral" and "positive") and confidence scores at the sentence and document-level. You can also send Opinion Mining requests using the Sentiment Analysis endpoint, which provides granular information about the opinions related to aspects (such as the attributes of products or services) in text |
| How to use Named Entity Recognition in Text Analytics | Topic | Step |
| What is the Translator service? | Topic | allows you to add multi-language user experiences in more than 70 languages |
| What is speech-to-text? | Topic | Speech-to-text, also known as speech recognition, enables real-time transcription of audio streams into text |
| What is speech translation? | Topic | speech translation service, which enables real-time, multi-language speech-to-speech and speech-to-text translation of audio streams |
| Example: Detect language with Text Analytics | Topic | Step |
| Get started with Text Analytics on Azure | Topic | Step |
| Example: How to extract key phrases using Text Analytics | Topic | evaluates a piece of text and identifies key talking points and popular mentions contained in the text |
| What is the Text Analytics API? | Topic | Step |
| Supported entity categories in the Text Analytics API v3 | Topic | Step |
| What is Language Understanding (LUIS)? | Topic | Step |
| Example user scenarios for the Text Analytics API | Topic | Step |
| What is Azure Content Moderator? | Topic | an AI service that lets you handle content that is potentially offensive, risky, or otherwise undesirable |
| Introduction to NLP | Topic | Language modeling aims to interpret the intent from a text statement and extract key information to discover the overall meaning from the text |
| Language and region support for LUIS | Topic | Step |
| Intro to speech recognition and synthesis | Topic | Consider the growing number of home and auto systems that you can control by speaking to them - issuing commands such as "turn off the lights", and soliciting verbal answers to questions such as "will it rain today?" |
| What is speech translation? | Topic | enables real-time, multi-language speech-to-speech and speech-to-text translation of audio streams |
| Get started with OCR on Azure | Topic | The ability to extract text from images is handled by the Computer Vision service, which also provides image analysis capabilities |
| Introduction to language translation | Topic | a translation service that takes into account the semantic context |
| What is Computer Vision? | Topic | Computer Vision can determine whether an image contains adult content, find specific brands or objects, or find human faces |
| Azure Media Services v3 overview | Topic | build solutions that achieve broadcast-quality video streaming, enhance accessibility and distribution, analyze content, and much more |
| Language Understanding | Topic | Converting a command into smart actions is an example of language modeling. LM interprets the intent of a text command and turns that command into an intent which can be converted into a smart action for a device |
| Text Analytics | Topic | An AI service that uncovers insights such as sentiment, entities, relations and key phrases in unstructured text |
| Get started with Text Analytics on Azure | Topic | Creating a transcript of a phone call is done using speech recognition. Mining customer opinions is an example of sentiment analysis. |
| Get started translation in Azure | Topic | The Translator Text service, which supports text-to-text translation. The Speech service, which enables speech-to-text and speech-to-speech translation |
| What is Bing Autosuggest? | Topic | Step |
| What is Bing Local Business Search? | Topic | Step |
| Language and region support for text and speech translation | Topic | Step |
| What is Form Recognizer? | Topic | Step |
| Speech to Text frequently asked questions | Topic | Step |
| How to recognize intents from speech using the Speech SDK for C# | Topic | Step |
| Text Analytics API (v3.0) | Topic | analyze unstructured text for tasks such as sentiment analysis, key phrase extraction and language detection. No training data is needed to use this API; just bring your text data. This API uses advanced natural language processing techniques to deliver best in class predictions |
| Quickstart: Use the Text Analytics client library and REST API | Topic | Step |
| Use Cognitive Services in Power Apps | Topic | Step |
| Create LUIS resources | Topic | Step |
| How to query the prediction runtime with user text | Topic | Step |
| Quickstart: Language Understanding (LUIS) client libraries and REST API | Topic | Step |
| Quickstart: Create a Cognitive Services resource using the Azure portal | Topic | Step |
| How to use batch transcription | Topic | Step |
| Language and voice support for the Speech service | Topic | Step |
| What is a voice assistant? | Topic | Step |
| Understand what good utterances are for your LUIS app | Topic | Step |
| Intents in your LUIS app | Topic | Step |
| Design with intent and entity models | Topic | Step |
| Extract data with entities | Topic | Step |
| Machine-learning features | Topic | Step |
| Prebuilt models | Topic | Step |
| Entities per culture in your LUIS model | Topic | Step |
| Add prebuilt models for common usage scenarios | Topic | Step |
| Prebuilt domain reference for your LUIS app | Topic | Step |
| What is machine translation? | Topic | Step |
Click here for My Notes on Conversational AI workloads
| Resource | Topic | Step |
|---|---|---|
| What are Cloud auto attendants? | Topic | Phone System provides auto attendants, which can be used to let external and internal callers move through a menu system to locate and place or transfer calls to users or departments in your organization |
| Cortana Skills Kit | Topic | Cortana is a personal digital assistant that keeps users informed and productive, helping them get things done across devices and platforms. Skills define the tasks that Cortana can accomplish. You can extend Cortana by adding your own skills that let your users interact with your service via Cortana. Cortana invokes the skills based on input from the user, either spoken or typed |
| How bots work | Topic | A bot is an app that users interact with in a conversational way, using text, graphics (such as cards or images), or speech. Azure Bot Service is a cloud platform. It hosts bots and makes them available to channels |
| Get started with QnA Maker and Azure Bot Service | Topic | QnA Maker. This cognitive service enables you to create and publish a knowledge base with built-in natural language processing capabilities. |
| Azure Bot Service. This service provides a framework for developing, publishing, and managing bots on Azure | ||
| What is the Bot Framework SDK? | Topic | The Bot Framework, along with the Azure Bot Service, provides tools to build, test, deploy, and manage intelligent bots |
| Get started with object detection on Azure | Topic | Step |
| What is speech-to-text? | Topic | Speech-to-text, also known as speech recognition, enables real-time transcription of audio streams into text |
| Get started with object detection on Azure | Topic | Step |
| Build a bot with QnA Maker and Azure Bot Service | Topic | organizations are turning to artificial intelligence (AI) solutions that make use of AI agents, commonly known as bots to provide a first-line of automated support through the full range of channels that we use to communicate. Bots are designed to interact with users in a conversational manner |
| Connect a bot to channels | Topic | A channel is a connection between communication applications and a bot. A bot, registered with Azure, uses channels to facilitate the communication with users. You can configure a bot to connect to any of the standard channels such as Alexa, Cortana, Facebook Messenger, and Slack |
| What is the Text Analytics API? | Topic | The Text Analytics API is a cloud-based service that provides Natural Language Processing (NLP) features for text mining and text analysis, including: sentiment analysis, opinion mining, key phrase extraction, language detection, and named entity recognition |
| Get started with object detection on Azure | Topic | The Custom Vision cognitive service in Azure enables you to create object detection models that meet the needs of many computer vision scenarios with minimal deep learning expertise and fewer training images |
| Understanding the Difference Between a Bot, a Chatbot, and a Robot | Topic | Step |
| An overview of semantic image segmentation | Topic | Step |
| Interactive Voice Response Bot | Topic | Step |
| AI and bot terms | Topic | Do not tell anyone the bots are rising up and taking over |
| Cortana Skills Bot Scenario | Topic | The Cortana Skills Bot extends Cortana to make it easy to book a mobile auto maintenance appointment using voice with context from your calendar |
| Bot scenarios | Topic | Step |
| Virtual Assistant Overview | Topic | Step |
| Add rich card attachments to messages the v3 C# SDK | Topic | A message exchange between user and bot can contain one or more rich cards rendered as a list or carousel |
| 5 CONVERSATIONAL AI USE CASES | Topic | Step |
| What is QnA Maker? | Topic | QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information |
| Importing from Datasources | Topic | Step |
| Edit QnA pairs in your knowledge base | Topic | Step |
| Azure resources for QnA Maker | Topic | Step |
| Manage QnA Maker resources | Topic | Step |
| Add Chit-chat to a knowledge base | Topic | Adding chit-chat to your bot makes it more conversational and engaging. The chit-chat feature in QnA maker allows you to easily add a pre-populated set of the top chit-chat, into your knowledge base (KB). This can be a starting point for your bot's personality, and it will save you the time and cost of writing them from scratch |
| Debug with the Emulator | Topic | The Bot Framework Emulator is a desktop application that allows bot developers to test and debug their bots, either locally or remotely |
| Bot Service templates | Topic | Basic Bot, form bot, LU Bot, Q&ABot, Proactive Bot |
| Bot Framework CLI tool | Topic | replaces the collection of standalone tools used to manage Bot Framework bots and related services |
| Introduction to Bot Framework Composer | Topic | Step |
| 3 Different Flavors For Building Chatbots With Microsoft | Topic | Step |
| Skills overview | Topic | Starting with version 4.7 of the Bot Framework SDK, you can extend a bot using another bot (a skill). A skill can be consumed by various other bots, facilitating reuse, and in this way, you can create a user-facing bot and extend it by consuming your own or 3rd party skills |
| Use Cognitive Services with natural language processing (NLP) to enrich bot conversations | Topic | Step |
| Use multiple LUIS and QnA models | Topic | If a bot uses multiple LUIS models and QnA Maker knowledge bases (knowledge bases), you can use Dispatch tool to determine which LUIS model or QnA Maker knowledge base best matches the user input |
| Use a Microsoft Bot Framework bot with Power Virtual Agents | Topic | use the Microsoft Bot Framework dispatcher tool to integrate an existing bot with a Power Virtual Agents bot |
| Plan your QnA Maker app | Topic | A single QnA Maker resource can host more than one knowledge base |
| Question and answer pair concepts | Topic | A knowledge base consists of question and answer (QnA) pairs. Each pair has one answer and a pair contains all the information associated with that answer |
| What is Form Recognizer? | Topic | a cognitive service that lets you build automated data processing software using machine learning technology. Identify and extract text, key/value pairs, selection marks, tables, and structure from your documents—the service outputs structured data that includes the relationships in the original file, bounding boxes, confidence and more |
| What is Speaker Recognition (Preview)? | Topic | service provides algorithms that verify and identify speakers by their unique voice characteristics using voice biometry. Speaker Recognition is used to answer the question “who is speaking?” |
| About skill bots | Topic | A skill is a bot. A skill manifest is a JSON file. |
| About skill consumers | Topic | A skill consumer is a bot that can call one or more skills. With respect to skills, a root bot is a user-facing bot that is also a skill consumer. From the user's perspective, the root bot is the bot they are interacting with. From the skill's perspective, the skill consumer is the channel over which it communicates with the user |
| Connect a bot to Web Chat | Topic | When you create a bot with the Framework Bot Service, the Web Chat channel is automatically configured for you |
| Connect a bot to Office 365 email | Topic | When a bot is configured to access an email account, it receives a message when a new email arrives. The bot can then respond as indicated by its business logic |
| Connect a bot to Microsoft Teams | Topic | Step |
| Introduction to Bot Framework Composer | Topic | Bot Framework Composer is an open-source visual authoring canvas for developers and multidisciplinary teams to build bots. Composer integrates language understanding services such as LUIS and QnA Maker and allows sophisticated composition of bot replies using Language Generation. Composer is available as a desktop application as well as a web-based component |
| Install Bot Framework Composer | Topic | Step |
| Create your first bot | Topic | Step |
| Publish a bot | Topic | Step |
If you liked this repo, give it a ⭐ and head over to: AI-100: Designing and Implementing an Azure AI Solution Study Notes