Book Overview & Buying
Table Of Contents
Feedback & Rating

Deep Learning with Microsoft Cognitive Toolkit Quick Start Guide

By : Meints

Buy this Book

Deep Learning with Microsoft Cognitive Toolkit Quick Start Guide

By: Meints

Buy this Book

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

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Getting Started with CNTK

The relationship between AI, machine learning, and deep learning

How does deep learning work?

What is CNTK?

Installing CNTK

Summary

Building Neural Networks with CNTK

Technical requirements

Basic neural network concepts in CNTK

Building your first neural network

Training the neural network

Making predictions with a neural network

Improving the model

Summary

Getting Data into Your Neural Network

Technical requirements

Training a neural network efficiently with minibatches

Working with small in-memory datasets

Working with large datasets

Taking control over the minibatch loop

Summary

Validating Model Performance

Technical requirements

Choosing a good strategy to validate model performance

Validating performance of a classification model

Validating performance of a regression model

Measuring performance for out-of-memory datasets

Monitoring your model

Summary

Working with Images

Technical requirements

Convolutional neural network architecture

Building convolutional networks

Improving model performance with data augmentation

Summary

Working with Time Series Data

Technical requirements

What are recurrent neural networks?

Recurrent neural networks variations

How do recurrent neural networks work?

Building recurrent neural networks with CNTK

Summary

Deploying Models to Production

Technical requirements

Using machine learning in a DevOps environment

Storing your models

Using Azure Machine Learning service to manage models

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

4 star

3 star

2 star

1 star

Working with small in-memory datasets

There are many ways in which you can feed data to the CNTK trainer. Which technique you should use depends on the size of the dataset and the format of the data. Let's take a look at how to work with smaller in-memory datasets first.

When you work with in-memory data in Python you will most likely use a framework such as Pandas or NumPy. These frameworks work with vectors and matrices of floating point or object data at their core and offer various levels of convenience when it comes to working with data.

Let's go over each of these libraries and explore how you can use data stored in these libraries to train your neural network.