Exam AI-100: Designing and Implementing an Azure AI Solution

Azure Bot Service: Rich Cards Signin Card

Enables a bot to request that a user sign in

Best means of ingesting messages from mobile devices

Event Hubs

Cognitive Services: Vision Face

- Face detection - Person and emotion identification in images -Face and grouping recognition

Speech To Text

Cognitive Service which can convert spoken conversation to text

Text Analytics

Cognitive Service which can identify named entities

Cognitive Services: Language Language Understanding (LUIS)

Cognitive Service which can interpret user requests, desires, and intents

HDInsight

- A cloud distribution of Hadoop components - A managed, full-spectrum, open-source analytics service in the cloud for enterprises - Lets you use open-source frameworks such as Hadoop, Apache Spark, Apache Hive, LLAP, Apache Kafka, Apache Storm, R, and more

ML.NET

- A free, open source, and cross platform machine learning framework for the .NET developer platform - Allows you to train, build, and ship custom machine learning models using C# or F# for a variety of ML scenarios - Includes automated machine learning (AutoML) and tools like ML.NET CLI and ML.NET Model Builder

Cognitive Services: Language Language Understanding (LUIS)

- A machine learning-based service to build natural language understanding into apps, bots, and IoT devices - Lets you quickly create enterprise-ready, custom models that continuously improve

Stream Analytics

- A real-time analytics and complex event-processing engine - Designed to analyze and process high volumes of fast streaming data from multiple sources simultaneously - Patterns and relationships can be identified in information - Information can be extracted from a number of input sources including devices, sensors, clickstreams, social media feeds, and applications - Patterns can be used to trigger actions and initiate workflows such creating alerts, feeding information to a reporting tool, or storing transformed data for later use - Is available on Azure IoT Edge runtime, and supports the same exact language or syntax as cloud

Azure Data Lake Storage Gen2

- A set of capabilities dedicated to big data analytics, built on Azure Blob storage Combines: - Features from Azure Data Lake Storage Gen1: file system semantics, directory, and file level security and scale - Features from Azure Blob storage: low-cost, tiered storage, high availability/disaster recovery capabilities

Cognitive Services: Search Bing Web Search

- Ad-free web search - Safe web search - Location-aware web search

Kubernetes

- Allows you to automate container provisioning, networking, load-balancing, security and scaling across all these nodes from a single command line or dashboard. - Automates the process of scaling, managing, updating and removing containers. In other words, it is a container orchestration platform

MML.Spark

- An ecosystem of tools aimed towards expanding the distributed computing framework Apache Spark in several new directions - Adds many deep learning and data science tools to the Spark ecosystem, including seamless integration of Spark Machine Learning pipelines with Microsoft Cognitive Toolkit (CNTK), LightGBM and OpenCV - Enables powerful and highly-scalable predictive and analytical models for a variety of datasources

Apache Kafka

- An open-source distributed streaming platform that can be used to build real-time streaming data pipelines and applications. - Provides message broker functionality similar to a message queue, where you can publish and subscribe to named data streams. - Distributed log that can hold data streams for long periods of time (beyond the 7 days provided by Event Hub)

Cognitive Services: Vision Computer Vision

- Analyze images for insights - Extract text from images, printed or handwritten - Generate high-quality thumbnails

Cognitive Services Decision Services and APIs

- Anomaly Detector - Content Moderator - Personalizer

Which Azure features/technologies can be used to automate your solution?

- Azure Automation Account - Azure Logic Apps - Azure Fundtions

Regulation and Compliance Tools

- Azure Compliance Manager - Azure Policy - Azure Security Center - Azure Information Protection

HDInsight Kafka

- Azure HDInsight service to process large volumes of streaming data / events - Real-time analytics engine

Key Vault

- Azure service/tool to securely store, manage, and access secrets for your AI application - A secret is anything that you want to tightly control access to, such as API keys, passwords, or certificates - A vault is a logical group of secrets.

Cognitive Services Web Search Services and APIs

- Bing Autosuggest - Bing Custom Search - Bing Entity Search - Bing Image Search - Bing News Search - Bing Spell Check - Bing Video Search - Bing Visual Search - Bing Web Search

Proactive Bot

- Bot that contacts a user based on some triggered event or lengthy job or an external event such as a state change in the system - Proactively sends messages to a user

TDSP Data Science Lifecycle

- Business Understanding - Data Acquisition & Understanding - Modeling - Deployment - Customer Acceptance

CPU vs. GPU

- CPU preferred for batch processing, web servers, analytics, and gaming - GPU preferred simulation, deep learning, graphics rendering, video editing, gaming and remote visualization

Cognitive Services: Language: LUIS Prebuilt Domains

- Calendar - Communication - Email - HomeAutomation - Note - Places - RestaurantReservation - ToDo - Utilities - Weather - Web

Question & Answer Bot

- Can be created by QnA Maker - Can also be created apart from QnA Maker using a template

What tools can be used to scale an AKS cluster dynamically?

- Cluster Autoscaler - Horizontal pod scaler

Cognitive Services: Vision Video Indexer

- Cognitive Service which can be used to tag scenes in videos and searchon those tags - Full analysis for visual & audio channels - Conducts facial, object, keyframe recognition, OCR & Transcription

RBAC Roles for Cognitive Services

- Cognitive Services Contributor - Cognitive Services Data Reader - Cognitive Services User

Cognitive Services Vision Services and APIs

- Computer Vision - Custom Vision - Face - Form Recognizer - Ink Recognizer - Video Indexer

Azure Container Registry (ACR)

- Container lifecycle management - Build, store, secure, scan, replicate, and manage container images and artifacts - Fully managed, geo-replicated instance of OCI Distribution - Connects across environments, including Azure Kubernetes Service and Azure Red Hat OpenShift, and across Azure services like App Service, Machine Learning, and Batch Features: - Geo-replication - OCI artifact repository - Automated container building and patching - Integrated security

Select the Processing Architecture

- Custom vs. pre-built - Deep Learning ≈ Neural Network

TDSP Components

- Data science lifecycle - Standardized project structure - Infrastructure and resources - Tools and utilities

Cognitive Services: Language: LUIS Entity

- Data you want to pull from an utterance, such as names, dates, product names, or any significant group of words - An utterance can include many ____________________s or none at all - A client application may need the data to perform its task - Use is optional - The primary purpose of ____________________s is to give the client application predictable extraction of data - An optional, secondary purpose is to boost the prediction of the intent or other ____________________with descriptors

Cognitive Services Top-Level Categories

- Decision - Langauge - Speech - Vision - Web Search

Text Analytics API

- Discover sentiment in text - Lets you learn what your customers are really saying about your product or brand when they send feedback

Azure Databricks

- Fast, optimized Apache Spark environment - Interactive workspace with built-in support for popular tools, languages, and frameworks - Native Azure Machine Learning integration - High-performance modern data warehousing in conjunction with Azure Synapse Analytics

Name some processes and regulations needed to conform with data privacy, protection, and regulatory requirements.

- Global: ISO, SOC 1, SOC2 - U.S. government: FedRAMP, DISA SRG, ITAR - Industry specific: PCI DSS, HIPAA, SOX - Region/country specific: GDPR, Australia IRAP, UK PASF

Cognitive Services: Language: LUIS Composite Entity

- Hierarchical entity - List entity: set of related words, including synonyms

Data Factory

- Hybrid data integration service that simplifies ETL at scale - Can ingest on-premises data from multiple sources into Azure Resources: - Mapping Data Flows - Predefined Templates - Triggers - Wrangling Data Flows - Control Flows

Cognitive Services Language Services and APIs

- Immersive Reader - Language Understanding (LUIS) - QnA Maker - Text Analytics - Translator Text

ML Processing Pipeline

- Ingest - Store - Analyze - Interact

Common uses for AKS

- Migrate existing application to cloud - Simplify deployment and management of microservices-based apps - Scale containerized applications

Machine Learning Pipeline Stages

- Prepare Data - Train Model - Package Model - Validate Model - Deploy Model - Monitor (Evaluate) Model

Cognitive Services APIs

- Provide programmatic access to Cognitive Services - Each Cognitive Service has a corresponding ______

Azure Search

- Provides a search capability as a service. - Enables the developers and business team to build a search-based application. - Provides search capability such as type-ahead suggestions, hit highlighting, faceted navigation and supports the linguistic features that are appropriate to specified language. - Can search across JSON, PDF and SQL Data

Cognitive Services: Language Translator Text

- Provides for machine-based text translation in near real-time - Auto language detection - Auto text translation - Customizable translation

Name some components and technologies required to connect service endpoints.

- REST: Representational State Transfer - Azure CLI: Command Line Interface - Subscription key - SDK: Software Development Kit

Cognitive Services: Language: LUIS Intent

- Represents a task or action the user wants to perform - Taxonomy of ____________________s is defined by the solution developer

Cognitive Services: Vision Computer Vision

- Service used to extract text from images - Process images and return information

Cognitive Services: Language: LUIS Entity Types

- Simple entity - Composite entity - Pattern.any - Prebuilt entity - Regular expression entity

Cognitive Services Speech Services and APIs

- Speech to Text - Text to Speech - Speech Translation - Speaker Recognition

Deep Learning

- The machine learning efforts of computers networked together to learn and train from vast amounts of data - Sometimes called a Neural Network

QnA Maker

- Tool to create FAQ-like databases that can be used by bots - ______ is a cloud-based Natural Language Processing (NLP) service that easily creates a natural conversational layer over your data - Can be used to find the most appropriate answer for any given natural language input, from your custom knowledge base (KB) of information - A client application for _________ is any conversational application that communicates with a user in natural language to answer a question - Examples of client applications include social media apps, chat bots, and speech-enabled desktop applications - Can support multiple languages in a single instance

LUDown

- Toolkit to build LUIS language understanding models and markdown files - Parses a .lu file into a .json model

Cognitive Services: Search Bing News Search

-Ad free news search results -Trending topic identification

Cognitive Services: Search Bing Video Search

-Ad free video search -Video topic & trend identification

Stream Analytics Scenarios

-Analyze real-time telemetry streams from IoT devices -Web logs/clickstream analytics -Geospatial analytics for fleet management and driverless vehicles -Remote monitoring and predictive maintenance of high value assets -Real-time analytics on Point of Sale data for inventory control and anomaly detection

Cognitive Services: Speech Speech Services

-Auto Speech to text transcription -Natural text to speech w/custom voice fonts -Real time speech translation

Cognitive Services: Search Bing Custom Search

-Custom search engine creation -Ad- free custom search results

Cognitive Services: Decision Personalizer

-Deliver rich personalized experiences in your apps -Deploy anywhere (cloud to edge) -Understand & easily manage the reinforcement learning loop

Cognitive Services: Decision Content Moderator

-Detect potential offensive & unwanted images -Filter possible profanity & undesirable text -Moderate adult and racy content in videos

Benefits of AKS

-Elastic provisioning -Faster end to end dev experience -Advanced identity & access mgt using AAD -Orchestration of containers across 29 regions

Cognitive Services: Vision Form Recognizer

-Extract text, key value pairs, & tables from documents. -Customize forms without manual labeling. -Deploy anywhere (cloud to edge)

Cognitive Services: Language Immersive Reader

-Help users read and comprehend text -Features for readers of all abilities

Cognitive Services: Search Bing Visual Search

-Identification of similar images and products -knowledge acquisition from images -Websource identification

Cognitive Services: Decision Anomaly Detector

-Monitor business health in real-time -Conduct IoT-remote monitoring -Leverage interactive data analytics

Cognitive Services: Language Text Analytics

-Named Entity Recognition -Key Phrase extraction -Text sentiment analysis

Cognitive Services: Search Bing Entity Search

-Named entity recognition & classification -Knowledge acquisition for named entities

Cognitive Services: Language QnA Maker

-QnA extraction from unstructured text -Knowledge base creation from collections of question and answer type resources (such as FAQs) -Semantic meaning for knowledge bases

Cognitive Services: Speech Speaker Recognition

-Speaker identification -Speaker verification

Cognitive Services: Search Bing Spell Check

-Web scale, multi lingual spell checking -Contextual spell checking

What is the minimum number of QnA Maker services that need to be deployed to support multiple languages and regions?

1 QnA Maker takes a parameter to specify a language, and can be shared across regions

Process to enable a bot to authenticate via Oauth (such as Gmailaccounts)

1. Create a client application in AAD 2. Create AAD B2C service 3. Configure the identity provided (such as Google/Facebook) in the B2C service 4. In the bot code, add the connection settings and OauthPrompt

Steps to run an AI container on AKS

1. Create an ACR instance 2. Create container image and store in ACR 3. Create AKS cluster

How would you implement approval of QnA data before uploading?

1. Use a Sharepoint List / PowerApp, or 2. Automate upload after data is approved from a source such as a spreadsheet

What is the minimum number of LUIS instances needed to be deployed to support two languages?

2 LUIS needs a unique instance for each language

Cognitive Service authentication

A Cognitive Service is accessed through a REST API, and that API authenticates via a token requested and approved using the key for the Cognitive Services resource. This is often done in application code via authentication classes that obtain the token given the endpoint and key, and then pass the token along with API calls.

Shared Access Signature (SAS)

A URI that grants restricted access rights to Azure Storage resources. You can provide a ____________________ to clients who should not be trusted with your storage account key but to whom you wish to delegate access to certain storage account resources. By distributing a ____________________ URI to these clients, you can grant them access to a resource for a specified period of time, with a specified set of permissions.

Azure Machine Learning (AML)

A cloud-based environment you can use to train, deploy, automate, manage, and track ML models

Bot Framework

A comprehensive framework for building enterprise-grade conversational AI experiences

Windows ML

A high-performance, reliable API for running ML inferences on Windows devices

Azure Bot Service: Rich Cards List Card

A scrolling list of items

Azure Cognitive Search (formerly Azure Search)

A search-as-a-service cloud solution that gives developers APIs and tools for adding a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications

Azure Data Factory

A service built for all data integration needs and skill levels. Easily construct ETL and ELT processes code-free within the intuitive visual environment, or write your own code. Visually integrate data sources using more than 90+ natively built and maintenance-free connectors at no added cost. Focus on your data—the serverless integration service does the rest.

Machine Learning Model Management

A.k.a. MLOps Azure Machine Learning provides the following MLOps capabilities: - Create reproducible ML pipelines. Register, package, and deploy models from anywhere - Capture the governance data required for capturing the end-to-end ML lifecycle - Notify and alert on events in the ML lifecycle - Monitor ML applications for operational and ML-related issues. - Automate the end-to-end ML lifecycle with Azure Machine Learning and Azure DevOps

Cognitive Services: Search Bing Image Search

Ad-free image search

Cognitive Services: Vision Ink Recognizer

An AI service that recognizes digital ink content, such as handwriting, shapes, and ink document layout

Team Data Science Process (TDSP)

An agile, iterative data science methodology to deliver predictive analytics solutions and intelligent applications efficiently. Helps improve team collaboration and learning. Contains a distillation of the best practices and structures from Microsoft and others in the industry that facilitate the successful implementation of data science initiatives.

Use Docker to run the specific Cognitive Service container

How do you run Cognitive Services on-premises?

Azure feature that can be used to enrich data using custom code

Azure Functions

IoT Edge modules

Azure IoT Edge lets you deploy and manage business logic on the edge in the form of ____________________. Azure IoT Edge ____________________ are the smallest computation units managed by IoT Edge, and can contain Microsoft services (such as Azure Stream Analytics), 3rd-party services or your own solution-specific code.

Cognitive Services Account

Azure resource that provides an API access key used to make calls to the various Cognitive Services APIs

Data Science Virtual Machine (DSVM)

Azure Virtual Machine images, pre-installed, configured and tested with several popular tools that are commonly used for data analytics, machine learning and AI training

Active Directory Reporting

Azure feature that can be used to audit application access to applications secured with AAD / Oauth

Speech to Text SDK

Azure feature to convert dictations in near-real time (and over 15 seconds in length)

Batch Transcription API

Azure feature to convert speech to text in bulk and at a scheduled timeafter collection

Cognitive Services Resources

Azure resources that provide the various Cognitive Services

Application Insights

Azure service that can be used to monitor scoring accuracy of a machine learning model A feature of Azure Monitor, it is an extensible Application Performance Management (APM) service for developers and DevOps professionals. Use it to monitor your live applications. It will automatically detect performance anomalies, and includes powerful analytics tools to help you diagnose issues and to understand what users actually do with your app.

Cosmos DB

Azure service that excels at storing JSON documents

Event Hubs

Azure service used to connect high volume message flow between endpoints; similar to Kafka

Azure Functions

Azure service useful to augment data in streams with data from othersources such as Azure SQL

Dispatch

Bot Framework Toolkit to build language models allowing you to dispatch between disparate components (such as QnA, LUIS and custom code) If a bot uses multiple LUIS models and QnA Maker knowledge bases (knowledge bases), you can use ____________________ tool to determine which LUIS model or QnA Maker knowledge base best matches the user input. The ____________________ tool does this by creating a single LUIS app to route user input to the correct model.

Chatdown

Bot Framework Toolkit to prototype mock conversations. Can be used to prototype mock conversations in markdown and convert the markdown to transcripts we can load and view in the new V4 Bot Framework Emulator.

Audio Card

Bot card to play an audio file?

Receipt Card

Bot card to present a receipt to the user, often containing a list ofitems, tax and total information, and other text.

Hero Card

Bot card to present a single large image, one or more buttons, and text?

Basic

Bot template that uses dialogs to respond to user input

Form

Bot template to guide a conversation with a user

Window functions

Capability of Stream Analytics to calculate an aggregate value on a subset of data based on a specific period of time

Record functions

Capability of Stream Analytics to filter pertinent data

Computer Vision: Face API

Cognitive Service that can be used to find / identity faces, facial expressions

Translator Text

Cognitive Service that can convert text from one language to another

Text Analytics

Cognitive Service that can determine the sentiment of text

Content Moderator: Image Moderation API

Cognitive Service used to find offensive content in images

Content Moderator: Text Moderation API

Cognitive Service used to find offensive content in text

Anomaly Detector

Cognitive Service which can be used to find unusual fluctuations in data

Cognitive Services: Vision Custom Vision

Customizable image recognition

Export the LUIS app from Azure into a container and run it in Kubernetes on something like Azure Stack

How do you run a LUIS app on-premises?

IoT Edge

Feature of Azure that allows running of AI and Azure features on IoT devices (things such as stream analytics and Azure functions)

Cognitive Services: Search Bing Local Business Search

Find local business results in your place of interest

Multiple Also, one endpoint implies that one API key is needed

From how many regions can a Cognitive Service endpoint can be accessed?

Deploy an app service, storage and Cognitive Service in that region.Data will not move/transit to/through another region, but perhaps out to the Internet via the web app

How can you ensure data for an AI app that uses a Cognitive Service stays inits own region?

Process to update keys for a Cognitive Service in an application

Generate new key, get a token from the endpoint, use the token for authorization in calls to the Cognitive Service

Blob Storage

Good place to store PDF's for processing by Cognitive Services

Enable soft delete and purge protection

How do you ensure key vault secrets are not accidentally deleted?

Azure Bot Service: Rich Cards Adaptive Card

Highly customizable card that can contain any combination of text, speech, images, buttons and input fields

1; you need a unique instance for each language

How many languages can be supported by a LUIS instance?

Multiple

How many languages can be supported by a QnA instance?

1. Get the encryption key from the user 2. Enable encryption using customer supported keys in key vault and blob storage 3. Upload the key to key vault

How would you encrypt blobs with a customer provided encryption key?

Cognitive Services: Vision Computer Vision

Image classification, scene & activity recognition in images, landmark recognition, OCR images

Endpoint URL and Access Key

Information needed to allow someone to call a Cognitive Service or amachine learning model exposed as a web service

IoT Hub

IoT Hub is a managed service, hosted in the cloud, that acts as a central message hub for bi-directional communication between your IoT application and the devices it manages. You can use Azure IoT Hub to build IoT solutions with reliable and secure communications between millions of IoT devices and a cloud-hosted solution backend. You can connect virtually any device to IoT Hub.

Cognitive Services: Language LUIS

Language Understanding Intelligent Service - Natural language - Learns over time - Model based on Intents, Utterances, and Entities

Speaker Recognition APIs

Lets you recognize specific voices and identify people

Azure Policy

Means of controlling the resources that specific users can deploy inAzure

Azure Stack

Microsoft product to run many of the features of Azure on-premises

- Azure AD Reporting - Azure Activity Logs - Azure Diagnostic Logs - Application Insights - Azure Monitor & Log Analytics Workspace

Name some Azure tools and technologies you would use for auditing.

Intelligent Kiosk

Open source app that showcases Azure Cognitive Services

Valid sources of data for Data Factory (a subset)

Oracle on-prem, SQL Server on-prem, Azure SQL, blob storage, tablestorage

Azure Bot Service: Rich Cards OAuth Card

Pre-configured authentication flow for various providers

Supported languages in Text Analytics

Primary - English, Chinese-Simplified, French, German, SpanishSecondary - seehttps://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/language-support#language-list-and-status

Azure Bot Service: Rich Cards Receipt Card

Provides a receipt to the user.

Cognitive Services Contributor

RBAC role that gives permission to fully manage keys for a Cognitive Service

Cognitive Services Data Reader

RBAC role that lets someone read Cognitive Services data.

Cognitive Services User

RBAC to only allow a user to list Cognitive Services Keys

How can you minimize data sent from IoT devices to the cloud?

Run cognitive services containers on the IoT devices

Cognitive Services: Search Bing Autosuggest

Search query autocomplete

Managed Identity

Service or VM requests Azure Active Directory to handle all authentication requests without providing direct access to a credential

Stream Analytics

Service that can be used to calculate aggregate results on a stream of data for a specific time window

Cognitive Services: Search Bing Statistics

Service that can provide search analytics such as local of the query, the last N query strings, number of calls, and geographic location

Azure Logic Apps

Simple means of creating apps without coding ___________________ is a cloud service that helps you schedule, automate, and orchestrate tasks, business processes, and workflows when you need to integrate apps, data, systems, and services across enterprises or organizations. _____________________ simplifies how you design and build scalable solutions for app integration, data integration, system integration, enterprise application integration (EAI), and business-to-business (B2B) communication, whether in the cloud, on premises, or both.

How can you keep PII out of the cloud when you use Cognitive Services?

Store data on-prem and run Cognitive Services in a container on premises

AKS cluster autoscaler vs. horizontal pod autoscaler

The cluster autoscaler watches for pods that can't be scheduled on nodes because of resource constraints. The cluster then automatically increases the number of nodes. The horizontal pod autoscaler uses the Metrics Server in a Kubernetes cluster to monitor the resource demand of pods. If an application needs more resources, the number of pods is automatically increased to meet the demand.

Data Analytics

The functions of ingesting and analyzing data.

Machine Learning

The method that computers use to take existing data, develop predictions, and then act without being explicitly programmed to do so

Data Transformation

The process of cleaning data and casting it into a format that can be used by downstream Data Analytics or Machine Learning.

PowerBI

Tool that can visualize data being sent through and IoT Hub

Compliance Manager

Tool to check that your LUIS bot is GDPR compliant

Azure CLI

Tool to use to deploy a bot to Azure

Azure Bot Service: Rich Cards Hero Card

Typically contains a single large image, one or more buttons, and a small amount of text.

Azure Bot Service: Rich Cards Thumbnail Card

Typically contains a single thumbnail image, some short text, and one or more buttons

How do you run Cognitive Services features on IoT devices?

Use Cognitive Services containers on the devices

Azure Bot Service: Rich Cards Card Collections

Used to return multiple items in a single response

Channels

Ways users can interact with your bots, e.g. web page, social media, etc.

Run cognitive services containers on the IoT devices

What can you do to take action on data on IoT devices as quickly as possible?

Azure CLI

What could you use to configure Application Insights on an ML model in AKS?

Install Azure Blob Storage on the IoT device

What is an easy means of supporting storing images on an IoT device for specific intervals of time?

IoT Hub

What is the best means of sending data from an IoT device into Azure?

Container Instances

What is the best technique to run a containerized AI solution on demand for short periods of time?

Compute Optimized

What is the best type of VM to perform deep learning?

GPU optimized

What is the best type of VM to perform image processing?

1 One instance can support multiple language detections and be sharedacross regions

What is the minimum number of Text Analytics instances needed to support multiple languages and regions?

1. Send from device to IoT Hub 2. Trigger a function on each IoT Hub message that calls Cognitive Service with the data

What is the process used to send data from an IoT device to Cognitive Services in Azure?

Increase the API from a PersonGroup to a LargePersonGroup

What is the simplest means of scaling Face API processing?

CPU

What kind of processor would you would favor for batch processing, web servers, and analytics?

GPU

What kind of processor would you would favor for simulation, deep learning, graphics rendering, video editing, gaming and remote visualization?

Create an index

What must you do prior to configuring Cognitive Search on top of Azure Search?

A voice signature

What needs to be created for each voice to be identified in an audio stream?

Text Analytics

Which API would you use to perform sentiment analysis?

Cognitive Services: Vision Computer Vision

Which Cognative Service would you use to identify celebrities in images?

- Iot Edge Devices - Container Instances - Azure Kubernetes Services (AKS)

Which azure compute services are able to run Cognitive Service containers?

SQL Server Azure SQL Database Azure SQL Data Warehouse

Which database platforms provide row-level security?

Thumbnail Card

Which kind of Bot Card can be used to display a single thumbnail image, one or more buttons, and text?

Animation Card

Which kind of Bot Card can be used to play animated GIF's or videos?

Video Card

Which kind of Bot Card can be used to play videos?

Receipt Card

Which kind of Bot Card can be used to present a receipt to the user, often containing a list of items, tax and total information, and other text?

Azure CLI

Which tool can you use to update machine learning models running in AKS?

Machine Learning Studio

Workbench where you can: - Register data - Train models - Evaluate models - Deploy models

Event Grid

____________________ allows you to easily build applications with event-based architectures. First, select the Azure resource you would like to subscribe to, and then give the event handler or WebHook endpoint to send the event to. ____________________ has built-in support for events coming from Azure services, like storage blobs and resource groups. It also has support for your own events, using custom topics. You can use filters to route specific events to different endpoints, multicast to multiple endpoints, and make sure your events are reliably delivered.

Azure Bot Service and Bot Framework

____________________ and ____________________ provide tools to build, test, deploy, and manage intelligent bots, all in one place. Through the use of modular and extensible framework provided by the SDK, tools, templates, and AI services developers can create bots that use speech, understand natural language, handle questions and answers, and more.

Batch Transcription API

____________________ is ideal for transcribing a large amount of audio in storage. By using the dedicated REST API, you can point to audio files with a shared access signature (SAS) URI and asynchronously receive transcription results.

Azure Notification Hubs

____________________ provide an easy-to-use and scaled-out push engine that allows you to send notifications to any platform (iOS, Android, Windows, Kindle, Baidu, etc.) from any backend (cloud or on-premises). Here are a few example scenarios: - Send breaking news notifications to millions with low latency. - Send location-based coupons to interested user segments. - Send event-related notifications to users or groups for media/sports/finance/gaming applications. - Push promotional contents to applications to engage and market to customers. - Notify users of enterprise events like new messages and work items. - Send codes for multi-factor authentication.