Advertisement

© 2018

Deep Learning with Azure

Building and Deploying Artificial Intelligence Solutions on the Microsoft AI Platform

Benefits

  • Provides a solid introduction to deep learning concepts, trends, and opportunities

  • Shows how to perform machine learning and deep learning using the latest tools and technologies on Microsoft AI

  • Teaches how to build and operationalize deep learning models on the Microsoft AI platform

  • Includes real-world deep learning recipes throughout the book to facilitate understanding

Book

Table of contents

  1. Front Matter
    Pages i-xxvii
  2. Getting Started with AI

    1. Front Matter
      Pages 1-1
    2. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 3-26
    3. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 27-51
    4. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 53-75
  3. Azure AI Platform and Experimentation Tools

    1. Front Matter
      Pages 77-77
    2. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 79-98
    3. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 99-128
  4. AI Networks in Practice

    1. Front Matter
      Pages 129-129
    2. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 131-160
    3. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 161-186
    4. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 187-208
  5. AI Architectures and Best Practices

    1. Front Matter
      Pages 209-209
    2. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 211-241
    3. Mathew Salvaris, Danielle Dean, Wee Hyong Tok
      Pages 243-259
  6. Back Matter
    Pages 261-284

About this book

Introduction

Get up-to-speed with Microsoft's AI Platform. Learn to innovate and accelerate with open and powerful tools and services that bring artificial intelligence to every data scientist and developer.

Artificial Intelligence (AI) is the new normal. Innovations in deep learning algorithms and hardware are happening at a rapid pace. It is no longer a question of should I build AI into my business, but more about where do I begin and how do I get started with AI?

Written by expert data scientists at Microsoft, Deep Learning with the Microsoft AI Platform helps you with the how-to of doing deep learning on Azure and leveraging deep learning to create innovative and intelligent solutions. Benefit from guidance on where to begin your AI adventure, and learn how the cloud provides you with all the tools, infrastructure, and services you need to do AI.

What You'll Learn:
  • Become familiar with the tools, infrastructure, and services available for deep learning on Microsoft Azure such as Azure Machine Learning services and Batch AI
  • Use pre-built AI capabilities (Computer Vision, OCR, gender, emotion, landmark detection, and more)
  • Understand the common deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs) with sample code and understand how the field is evolving
  • Discover the options for training and operationalizing deep learning models on Azure
This book is for professional data scientists who are interested in learning more about deep learning and how to use the Microsoft AI platform. Some experience with Python is helpful.

Mathew Salvaris, PhD is a senior data scientist at Microsoft in the Cloud and AI division, where he works with a team of data scientists and engineers building machine learning and AI solutions for external companies utilizing Microsoft's Cloud AI platform. 

Danielle Dean, PhD is a principal data science lead at Microsoft in the Cloud and AI division, where she leads a team of data scientists and engineers building artificial intelligence solutions with external companies utilizing Microsoft’s Cloud AI platform. 

Wee Hyong Tok, PhD is a principal data science manager at Microsoft in the Cloud and AI division. He leads the AI for Earth Engineering and Data Science team, where his team of data scientists and engineers are working to advance the boundaries of state-of-the-art deep learning algorithms and systems.

Keywords

Azure AI Platform Microsoft Azure Data Science Deep Learning Machine Learning Wee Hyong Tok Danielle Dean Mathew Salvaris TensorFlow Cognitive Services CIFAR-10 GANS Microsoft AI Artificial Intelligence Custom Vision Transfer Learning Cloud computing

Authors and affiliations

  1. 1.LondonUK
  2. 2.WestfordUSA
  3. 3.RedmondUSA

About the authors

Mathew Salvaris, PhD is a senior data scientist at Microsoft in the Cloud and AI division, where he works with a team of data scientists and engineers building machine learning and AI solutions for external companies utilizing Microsoft's Cloud AI platform. He enlists the latest innovations in machine learning and deep learning to deliver novel solutions for real-world business problems, and to leverage learning from these engagements to help improve Microsoft's Cloud AI products. Prior to joining Microsoft, he worked as a data scientist for a fintech startup where he specialized in providing machine learning solutions. Previously, he held a postdoctoral research position at University College London in the Institute of Cognitive Neuroscience, where he used machine learning methods and electroencephalography to investigate volition. Prior to that position, he worked as a postdoctoral researcher in brain computer interfaces at the University of Essex. Mathew holds a PhD and MSc in computer science. 

Danielle Dean, PhD is a principal data science lead at Microsoft in the Cloud and AI division, where she leads a team of data scientists and engineers building artificial intelligence solutions with external companies utilizing Microsoft’s Cloud AI platform. Previously, she was a data scientist at Nokia, where she produced business value and insights from big data through data mining and statistical modeling on data-driven projects that impacted a range of businesses, products, and initiatives. She has a PhD in quantitative psychology from the University of North Carolina at Chapel Hill, where she studied the application of multi-level event history models to understand the timing and processes leading to events between dyads within social networks.

Wee Hyong Tok, PhD is a principal data science manager at Microsoft in the Cloud and AI division. He leads the AI for Earth Engineering and Data Science team, where his team of data scientists and engineers are working to advance the boundaries of state-of-art deep learning algorithms and systems. His team works extensively with deep learning frameworks, ranging from TensorFlow to CNTK, Keras, and PyTorch. He has worn many hats in his career as developer, program/product manager, data scientist, researcher, and strategist. Throughout his career, he has been a trusted advisor to the C-suite, from Fortune 500 companies to startups. He co-authored one of the first books on Azure machine learning, Predictive Analytics Using Azure Machine Learning, and authored another demonstrating how database professionals can do AI with databases, Doing Data Science with SQL Server. He has a PhD in computer science from the National University of Singapore, where he studied progressive join algorithms for data streaming systems.


Bibliographic information

Industry Sectors
Pharma
Automotive
Chemical Manufacturing
Biotechnology
IT & Software
Telecommunications
Law
Consumer Packaged Goods
Engineering
Finance, Business & Banking
Electronics
Energy, Utilities & Environment
Aerospace