David Voss - Azure AI Fundamentals: Study Guide and Practice Exam for the Microsoft AI-900 Exam

Azure AI Fundamentals: Study Guide and Practice Exam for the Microsoft AI-900 Exam — read online for free the complete book (whole text) full work

Below is the text of the book, divided by pages. System saving the place of the last page read, allows you to conveniently read the book "Azure AI Fundamentals: Study Guide and Practice Exam for the Microsoft AI-900 Exam" online for free, without having to search again every time where you left off. Put a bookmark, and you can go to the page where you finished reading at any time.

Light

Font size:

↓

↑

Georgia Tahoma Arial Verdana

Reset

Interval:

↓

↑

Bookmark:

Make

1234567...12

Azure AI Fundamentals

Study Guide and Practice Questions
for the Microsoft AI-900 Exam

David Voss

Copyright 2020 by David H. Voss

All rights reserved. No part of this book may be reproduced or used in any manner without written permission of the copyright owner except for the use of quotations in a book review. For more information, address: dhvoss@voss.ai

FIRST EDITION

ISBN: 9798671153989

www.voss.ai

Introduction

Audience

We created this study guide for those interested in gaining a foundational knowledge of the Microsoft Azure Artificial Intelligence services. It provides you with the information you need to pass the Microsoft AI Foundations exam (AI-900). You do not need a programming or mathematical background to read this book.

Additional Online Resources

VOSS.AI provides you with additional online resources for your studies. Specifically, you can find further study questions for the AI-900 exam. We will add new items for AI-900 and the other Azure AI exams frequently.

About the Author

David Voss has worked in IT since 1996. He began his career as a Microsoft Certified Systems Engineer, implementing and supporting various Microsoft systems. David then focused on LAN, WAN, and Data Center consulting for large businesses and Internet Service Providers. He obtained many Cisco Routing and Switching certifications, including Cisco Certified Internetwork Expert. More recently, David grew an appreciation for the transformative nature of Artificial Intelligence in the IT industry. He believes anyone who wants to learn AI should have the opportunity to do so and created VOSS.AI with that mission in mind.

About VOSS.AI

AI for All VOSS.AI creates products and services for anyone who has an interest in learning about Artificial Intelligence. We have chosen Microsoft AI as our platform of choice because Microsoft has made a concerted effort to ensure their AI products are accessible to those new to the field.

Study with Confidence

VOSS.AI is committed to the integrity of the exams, as well as you as a student. This study guide does not contain any material that compromises the integrity of any Microsoft exam. All materials, including practice questions, were developed using the syllabus for the exam and thorough research of published articles.

Table of Contents

Chapter 1 - Identify Features of Common AI Workloads

In this chapter, we will identify the features of the following:

• Prediction/Forecasting Workloads
• Anomaly Detection Workloads
• Computer Vision Workloads
• Natural Language Processing
• Conversational AI Workloads

Prediction/Forecasting Workloads

The hallmark of Prediction/Forecasting workloads is when your data has two available options (e.g., yes/no, true/false). AI can learn to associate historical patterns with future outcomes. You would typically use the Prediction/Forecasting model to answer either/or questions. Here are a few examples:

• Which applicants are most likely to qualify for a loan?
• Which customers are likely to attend our new store opening?
• Which leads will likely purchase online instead of in the store?

Anomaly Detection Workloads

Anomaly detection workloads typically are identified by an imbalanced data set. An imbalanced dataset occurs when several observations belonging to one class are much higher or lower than those belonging to the other classes. For example, if a small percentage of transactions are fraudulent, those certainly are the anomalies that we will want to capture. Here are a few other examples of when you would be working with an imbalance data set for anomaly detection:

• Identifying network traffic that has a signature of a network intrusion
• Verifying if values entered into a system are inaccurate
• Discovering abnormal patterns in employee time reporting

One of the challenges in working with data sets for anomaly detection is that by their very nature, anomalies are rare. It can be challenging to collect a representative sample to use for modeling. There are algorithms developed to overcome the challenges posed by imbalanced data sets.

Computer Vision Workloads

Computer Vision workloads contain images. That image data can take many forms, including but not limited to digital pictures, video, multi-dimensional data from medical scanners, and multi-input video such as views from multiple cameras. With the progress and increased usage of mobile phone cameras and video, the amount of data available for vision workloads has grown exponentially. Due to the rapid availability of computing power, accuracy rates for object identification and classification have increased exponentially. Today's computer vision systems are often more accurate than humans at image analysis. Here are just a few examples:

• Evaluating images of cancerous tumors
• Facial recognition
• Environmental impact analysis of satellite images

Natural Language Processing and Knowledge Mining Workloads

The typical workload for National Language Processing (NLP) and Knowledge Mining workloads will be words, phrases, sentences, and potentially entire articles, technical publications, wiki's or books. Machine Learning is then used to find patterns to achieve a goal. For example, many universities now feed student papers into a system that can identify if the student wrote it on their own or plagiarized portions of their submission. Other examples of using NLP:

• Language translation software
• Chatbots
• Search, grammar, and spellcheck improvements
• The primary proofreader and editor for this study guide (grammerly.com)

Knowledge mining allows organizations to gain insights from content much faster than before. Historically, humans obtained information using a trained eye. By leveraging various computing capabilities, AI can do this much faster and more comprehensively. Here are a few examples:

• Identify Quality of Service information within an enormous technical article on IP voice design
• Identify entities of importance within legal documents and flag them for review
• Quickly provide the right answer to a customer question

Conversational AI Workloads

Conversational AI is a set of technologies that enable systems to simulate real conversations with humans. Conversational AI is different than the chatbots used in Natural Language Processing because it may include voice input and output. At its best, Conversational AI can engage in human-like dialogue. Therefore, the workload for conversational will consist of the same data set as NLP (e.g., words, phrases, books, etc.) and audio. For example, if patients have frequently asked, "When I can pick up my medication?" the AI system will input, learn from, and be able to provide answers to that question.

Summary of AI Workloads

Workload	Data
Prediction/Forecasting	Binary (e.g. true/false, yes/no)
Anomaly Detection	Imbalanced
Computer Vision	Images, Video
Natural Language Processing	Words, phrases, publications, wiki's

Next page

1234567...12

Light

Font size:

↓

↑

Georgia Tahoma Arial Verdana

Reset

Interval:

↓

↑

Bookmark:

Make

Similar books «Azure AI Fundamentals: Study Guide and Practice Exam for the Microsoft AI-900 Exam»

Look at similar books to Azure AI Fundamentals: Study Guide and Practice Exam for the Microsoft AI-900 Exam. We have selected literature similar in name and meaning in the hope of providing readers with more options to find new, interesting, not yet read works.

Shimon Brathwaite

MCA Microsoft Certified Associate Azure Security Engineer Study Guide: Exam AZ-500

Rithin Skaria

MCA Microsoft Certified Associate Azure Administrator Study Guide: Exam AZ-104

Jake Switzer

MC Microsoft Certified Azure Data Fundamentals Study Guide: Exam DP-900

Julian Sharp

Exam Ref AI-900 Microsoft Azure AI Fundamentals

Jack Hyman

Microsoft Certified Azure Fundamentals All-in-One Exam Guide (Exam AZ-900)

Daniel A. Seara

Exam Ref DP-900 Microsoft Azure Data Fundamentals

Sjoukje Zaal

Microsoft Azure Architect Technologies: Exam Guide AZ-300: A guide to preparing for the AZ-300 Microsoft Azure Architect Technologies certification exam

Rahul Sahay

Microsoft Azure Architect Technologies Study Companion: Hands-on Preparation and Practice for Exam AZ-300 and AZ-303

IT Pro - York University.

CompTIA IT Fundamentals+ All-in-One Exam Guide (Exam FC0-U61)

Jim Cheshire

Exam Ref AZ-900 Microsoft Azure Fundamentals

Michael Washam

Exam Ref AZ-103 Microsoft Azure Administrator

Haishi Bai

Exam Ref 70-535 Architecting Microsoft Azure Solutions

Discussion, reviews of the book Azure AI Fundamentals: Study Guide and Practice Exam for the Microsoft AI-900 Exam and just readers' own opinions. Leave your comments, write what you think about the work, its meaning or the main characters. Specify what exactly you liked and what you didn't like, and why you think so.