Book Image

Deep Learning with Microsoft Cognitive Toolkit Quick Start Guide

By : Willem Meints
Book Image

Deep Learning with Microsoft Cognitive Toolkit Quick Start Guide

By: Willem Meints

Overview of this book

Cognitive Toolkit is a very popular and recently open sourced deep learning toolkit by Microsoft. Cognitive Toolkit is used to train fast and effective deep learning models. This book will be a quick introduction to using Cognitive Toolkit and will teach you how to train and validate different types of neural networks, such as convolutional and recurrent neural networks. This book will help you understand the basics of deep learning. You will learn how to use Microsoft Cognitive Toolkit to build deep learning models and discover what makes this framework unique so that you know when to use it. This book will be a quick, no-nonsense introduction to the library and will teach you how to train different types of neural networks, such as convolutional neural networks, recurrent neural networks, autoencoders, and more, using Cognitive Toolkit. Then we will look at two scenarios in which deep learning can be used to enhance human capabilities. The book will also demonstrate how to evaluate your models' performance to ensure it trains and runs smoothly and gives you the most accurate results. Finally, you will get a short overview of how Cognitive Toolkit fits in to a DevOps environment
Table of Contents (9 chapters)

What this book covers

Chapter 1, Getting Started with CNTK, introduces you to the CNTK framework and the world of deep learning. It explains how to install the tools on your computer and how to use a GPU with CNTK.

Chapter 2, Building Neural Networks with CNTK, explains how to build your first neural network with CNTK. We dive into the basic building blocks and see how to train a neural network with CNTK.

Chapter 3, Getting Data into Your Neural Network, shows you different methods of loading data for training neural networks. You'll learn how to work with both small datasets, and datasets that don't fit in your computer's memory.

Chapter 4, Validating Model Performance, teaches you how to work with metrics to validate the performance of your neural network. You'll learn how to validate regression models and classification models and what to look for when trying to debug your neural network.

Chapter 5, Working with Images, explains how to use convolutional neural networks to classify images. We'll show you the building blocks needed to work with spatially-ordered data. We'll also show you some of the most well-known neural network architectures for working with images.

Chapter 6, Working with Time Series Data, teaches you how to use recurrent neural networks to build models that can reason over time. We'll explain the various building blocks that you need to build and validate a recurrent neural network yourself, based on a IoT sample.

Chapter 7, Deploying Models to Production, shows you what it takes to deploy deep learning models to production. We'll take a look at a DevOps environment with a continuous integration/continuous deployment (CI/CD) pipeline to teach you what it takes to train and deploy models in an agile engineering environment. We'll show you how you can use a tool such as Azure Machine Learning service to take your machine learning efforts to the next level.