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)

Monitoring your model

Now that we've done some validation on our models, it's time to talk about monitoring your model during training. You saw some of this before in the section Measuring classification performance in CNTK and the previous Chapter 2, Building Neural Networks with CNTK, through the use of the ProgressWriter class, but there are more ways to monitor your model. For example: you can use TensorBoardProgressWriter. Let's take a closer look at how monitoring in CNTK works and how you can use it to detect problems in your model.

Using callbacks during training and validation

CNTK allows you to specify callbacks in several spots in the API. For example: when you call train on a loss function, you can...