Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2018 | Buch

Introduction to Artificial Intelligence Kapitel lesen Erstes Kapitel lesen

Deep Learning with Azure

Building and Deploying Artificial Intelligence Solutions on the Microsoft AI Platform

verfasst von: Mathew Salvaris, Danielle Dean, Wee Hyong Tok

Verlag: Apress

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

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 LearnBecome 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

Who 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.

Inhaltsverzeichnis

Frontmatter

Getting Started with AI

Frontmatter
Chapter 1. Introduction to Artificial Intelligence
Abstract
Intelligence can be defined in many ways, from the ability to learn to deal with new situations to the ability to make the right decisions according to some criterion, for example (Bengio, 2010). Standard computers and even basic calculators can be thought to be intelligent in some ways, as they can compute an outcome based on human-programed rules. Computers are extremely useful for mundane operations such as arithmetic calculations, and the speed and scale at which they can tackle these problems has greatly increased over time.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Chapter 2. Overview of Deep Learning
Abstract
In Chapter 1, we gave an overview of AI and the basic idea behind deep learning. We discussed how deep learning—applying artificial neural network models with a large number of layers—has yielded state-of-the art results for several research areas, such as image classification, object detection, speech recognition, and natural language processing.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Chapter 3. Trends in Deep Learning
Abstract
This chapter discusses some of the trends in deep learning and related fields. We cover specifically which trends might be useful for what tasks as well as discuss some of the methods and ideas that could have far-reaching implications but have yet to be applied to many real-world problems. We finish by covering briefly some of the current limitations of deep learning as well as some other areas of AI that seem to hold promise for future AI applications, and discuss briefly some of the ethical and legal implications of deep learning applications.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok

Azure AI Platform and Experimentation Tools

Frontmatter
Chapter 4. Microsoft AI Platform
Abstract
This chapter introduces the Microsoft AI Platform, which is a set of services, infrastructure, and tools for building intelligent applications powered by AI. The Microsoft AI Platform runs on the Microsoft Azure cloud computing environment, which provides computing as a utility where you pay for what you use rather than what you own. For more details on the broader Azure Platform, please see the e-book Developer’s Guide to Microsoft Azure (Crump & Luijbregts, 2017). The Microsoft AI Platform enables data scientists and developers to create AI solutions in an efficient and cost-effective manner.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Chapter 5. Cognitive Services and Custom Vision
Abstract
Chapter 4 introduced the tools, infrastructure, and services that are available to build the next generation of intelligent applications. These together form a platform that empowers data scientists and developers to build, train, and deploy ML and deep learning models on the intelligent cloud and intelligent edge.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok

AI Networks in Practice

Frontmatter
Chapter 6. Convolutional Neural Networks
Abstract
CNNs are a prime example of neuroscience influencing deep learning (LeCun, Bottou, Bengio, & Haffner, 1998). These neural networks are based on the seminal work done by Hubel and Wiesel (1962). They discovered that individual neuronal cells in the visual cortex responded only to the presence of visual features such as edges of certain orientations. From their experiments they deduced that the visual cortex contains a hierarchical arrangement of neuronal cells. These neurons are sensitive to specific subregions in the visual field, with these subregions being tiled to cover the entire visual field. They in fact act as localized filters over the input space, making them well suited to exploiting the strong spatial correlation found in natural images. CNNs have been immensely successful in many computer vision tasks not just because of the inspiration drawn from neuroscience, but also due to the clever engineering principles employed. Although they have traditionally been used for applications in the field of computer vision such as face recognition and image classification, CNNs have also been used in other areas such as speech recognition and natural language processing for certain tasks.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Chapter 7. Recurrent Neural Networks
Abstract
The previous chapter showed how a deep learning model—specifically CNNs—could be applied to images. The process could be decoupled into a feature extractor that figures out the optimal hidden-state representation of the input (in this case a vector of feature maps) and a classifier (typically a fully connected layer). This chapter focuses on the hidden-state representation of other forms of data and explores RNNs. RNNs are especially useful for analyzing sequences, which is particularly helpful for natural language processing and time series analysis.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Chapter 8. Generative Adversarial Networks
Abstract
For many AI projects, deep learning techniques are increasingly being used as the building blocks for innovative solutions ranging from image classification to object detection, image segmentation, image similarity, and text analytics (e.g., sentiment analysis, key phrase extraction). GANs, first introduced by Goodfellow et al. (2014), are emerging as a powerful new approach toward teaching computers how to do complex tasks through a generative process. As noted by Yann LeCun (at http://bit.ly/LeCunGANs ), GANs are truly the “coolest idea in machine learning in the last 20 years.”
Mathew Salvaris, Danielle Dean, Wee Hyong Tok

AI Architectures and Best Practices

Frontmatter
Chapter 9. Training AI Models
Abstract
Training AI models is usually more demanding than training standard ML models because they are processing intensive and often the data sets involved are larger. That is why if you are serious about deep learning you have to have access to GPUs. In Azure there are a number of ways you can make use of GPUs, on single VMs or in orchestrated clusters of them. In this chapter, we summarize several of the most common methods available as well as the pros and cons of each. Then we expand on the code we wrote in Chapter 6, which used a VGG-like CNN to tackle the CIFAR10 data set using the DLVM as the computing environment. In this chapter, we extend to other training options such as Batch AI and Batch Shipyard, which can both be useful for scaling up or scaling out training. We finish by highlighting briefly some of the other methods of training AI models on Azure that are not as common but might be useful depending on the problem at hand.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Chapter 10. Operationalizing AI Models
Abstract
The previous chaptercovered what constitutes an AI model, the different types of models we can create, and how to train and build these models. An AI model does not become useful until it is deployed somewhere and consumed by the end user. This chapter describes the various options available on Azure to deploy your models. We provide general guidelines on what to use and when, but this is by no means an exhaustive guide to the Azure platform. In the following sections we discuss the metrics over which we compare the various deployment platforms. Then we discuss the platforms we have found to be suitable for deploying ML models and highlight their pros and cons. We also present simple use cases and architectures for each of them so that you get an idea of how they would fit into a larger solution. We also provide a step-by-step tutorial for deployment of a CNN to Azure Kubernetes Services (AKS) with GPU nodes as a hands-on guide for one recommended option for building a real-time request–response AI system.
Mathew Salvaris, Danielle Dean, Wee Hyong Tok
Backmatter
Metadaten
Titel
Deep Learning with Azure
verfasst von
Mathew Salvaris
Danielle Dean
Wee Hyong Tok
Copyright-Jahr
2018
Verlag
Apress
Electronic ISBN
978-1-4842-3679-6
Print ISBN
978-1-4842-3678-9
DOI
https://doi.org/10.1007/978-1-4842-3679-6