Trivedi Microsoft Azure AI Fundamentals Certification Companion

Guide to Prepare for the AI-900 Exam
1. Auflage 2023
ISBN: 978-1-4842-9221-1
Verlag: APRESS
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 189 Seiten, eBook

Reihe: Certification Study Companion Series

Prepare for the Azure AI Fundamentals certification examination. This book covers the basics of implementing various Azure AI services in your business. The book not only helps you get ready for the AI-900 exam, but also helps you get started in the artificial intelligence (AI) world. 
The book starts with a short overview of the AI-900 exam and takes you through the exam prerequisites and the structure of the exam. You will then learn basic and advanced AI in Azure. Principles of responsible AI, Azure Machine Learning (ML), Azure Cognitive Services, and Bot Services are covered, followed by a practice test. You will go through ML fundamental concepts, model training, and validation along with case studies and a practice test for better preparation. The book includes the fundamentals of Azure and computer vision cognitive services. Various vision services and face services are demonstrated as well as analyzing image and text using OCR. You will understand concepts of natural language processing (NLP) such as text analysis, language modelling, entity recognition, sentiment analysis, speech recognition, and synthesis and also learn how to leverage Microsoft Azure for NLP. 
After reading this book, you will be able to implement various Azure AI services and prepare for the Azure AI Fundamentals certification exam, AI-900.

What Will You Learn

• Understand AI fundamentals and responsibilities
• Know the Microsoft Azure offerings for AI
• Understand foundational concepts for ML and Azure offerings for ML
• Understand Azure Cognitive Services such as Custom Vision, Face, Form Recognizer, Text-to-Speech, and Image Analysis

Who This Book Is For
Azure and AI users working with ML services

Zielgruppe

Professional/practitioner

Autoren/Hrsg.

Trivedi, Krunal S.

Inhaltsverzeichnis

Chapter 1:  AI-900 Overview of Exam Preparation

Chapter Goal:The chapter introduces the exam to the learners. The exam object-

ives are made clear to the readers. Readers gain understanding about exam modules, module weightage, and how much to expect from each module throughout the examination. Links to pertinent resources on Microsoft Learn would be provided for the readers' benefit.

No of pages: 2           

Subtopics

1.      Exam Overview

2.      Who is this exam for – Exam prerequisite

3.       Modules and weightage in exam

4.      Module Description

Chapter 2:  Fundamentals of Artificial Intelligence

Chapter Goal:

The chapter's objective is to introduce some foundational, high-level elements. These concepts would be explored in depth over the next chapters of the books.

No of pages: 15

Sub - Topics  

1.        What is Artificial Intelligence?

2.        Understanding Artificial Intelligence workloads

3.        Principles of Responsible AI

4.        Understanding Artificial Intelligence in Microsoft Azure

5.        AI Services in Microsoft Azure

1.      Azure Machine Learning

2.      Azure Cognitive Service

3.      Azure Bot Service

4.      Azure Cognitive Search

6.       Module Review

7.       Introspective Practice

8.       Solutions to the practice test

9.       References: Microsoft Learn

Chapter 3: Machine Learning Fundamental Concepts

Chapter Goal: This chapter make reader familiar to the Machine Learning fundamentals introducing Machine Learning, Types of Machine Learning, Model training and validation. Here readers will also get to know about various tools used for Machine Learning.

No of pages: 30

Sub - Topics: 

1.      What is Machine Learning?

2.      Describing Core Machine Learning Concepts

1.      Dataset, Features and Labels

2.      Machine Learning Algorithms in brief

3.      Machine Learning Workflow

4.      Model Evaluation Metrics

3.      Types of Machine Learning

1.      Regression

2.      Classification

3.      Clustering

3. The two importance elements: Model Training and Validation

4.  Introducing Azure Machine Learning

5.  Tools for Azure Machine Learning

1        Azure Machine Learning Studio

2    Azure Machine Learning Designer

6 What is Automated Machine Learning?

7. Practical Labs:

Using Azure Machine Learning Designer to build a regression model Using Azure Machine Learning Designer, create a classification model

Using Azure Machine Learning Designer to build a clustering model

8. Module Review

9. Introspective Practice

10. Solutions to the practice test

11. References: Microsoft Learn

Chapter 4:  Computer Vision

Chapter Goal: The chapter introduces readers to the fundamentals of Azure Cognitive Services in brief, as well as in depth knowledge of Computer Vision Cognitive Service.

No of pages: 50

Sub - Topics:

1.  Getting Started with Azure Cognitive Service

       Benefits of Cognitive Service

       Azure Cognitive Service: Speech

                                                Language

                                                Vision

                                                Decision

                                                Open AI Service

2.      What is Computer Vision?

3.      Computer Vision Core Elements: Image Classification and Object Detection

3.   Computer Vision Application

4.      Exploring Various Vision Service

1.      Computer Vision

2.      Custom Vision

3.      Face

4.      Form Recognizer

5.       Understanding of OCR

6.       Practical Labs:

• 1.       Analysing image with Computer Vision
• 2.       Training Models with Custom Vision
• 3.       Using Face Service to analyse faces
• 4.       Analysing text with Computer Vision Service using OCR

7.       Introspective Practice Test

8.       Solutions to the practice test

9.       References: Microsoft Learn

Chapter 5: Fundamentals of Natural Language Processing

Chapter Goal:           This chapter introduces readers with the responsibilities of Natural Language processing such as text analysis, language modelling, entity recognition, sentiment analysis, speech recognition and synthesis and how to leverage Microsoft Azure for NLP.

   No. of Pages: 50

1.      Getting Started with Natural Language Processing

1.      What is Natural Language Processing?

2.      Core NLP Responsibilities

1.      Text analysis and entity recognition

2.      Sentiment analysis

3.      Speech recognition and synthesis

4.      Machine Translation

5.      Semantic Language modelling

2.      AI for Conversational Interactions

3.      Microsoft Azure for NLP

1.      Core Azure NLP workloads: Language, Speech and Translator

2.      Language:

1.      Language Detection

2.      Key phrase extraction

3.      Entity Detection

4.      Sentiment Analysis

5.      Question Answering

6.      Conversational Language Understanding

3.      Speech:

1.      Text to speech

2.      Speech to text

3.      Speech translation

4.      Translator

1.      Text Translation

2.      Microsoft Azure platform for Conversational AI

1.      Azure Bot Service

3.      Practical Labs:

• 1.      Text analysis with text-analysis-service
• 2.      Using the Speech service's speech-to-text capabilities to transcribe audible speech to text.
• 3.      Using the Speech service's text-to-speech capabilities to generate audible speech from text.
• 4.      Using translator service to convert text
• 5.      Language Understanding Application Development
• 6.      Developing a Q&A generator with Azure Bot Service
• 7.      Provisioning chat bot using Microsoft Azure Bot Service

4.      Introspective Test

5.      Solutions to the Practice Test

6.      References: Microsoft Learn

Über Autor(innen)

Krunal S. Trivedi is a Microsoft Certified Trainer and a Microsoft Azure MVP for the past 5 years. He has been providing technical training on a variety of Microsoft and non-Microsoft technologies to IT corporations all over the world for the past 14 years. He is an enthusiastic speaker, trainer, writer, and author. Krunal is actively involved in project architecting, building solutions using modern edge technologies such as React, Angular, Docker, and Microsoft Azure, in addition to training. He has worked on numerous projects and products, from requirement gathering to project deployment using the Agile methodology and DevOps pipeline.