Category Archives: CNTK

Posts about the Microsoft CNTK deep learning code library

Introduction to DNN Image Classification Using CNTK

I wrote an article titled “Introduction to DNN Image Classification Using CNTK” in the July 2018 issue of Microsoft MSDN Magazine. See https://msdn.microsoft.com/en-us/magazine/mt847190. Image classification is a standard problem in machine learning. If you have an image (typically a photograph), … Continue reading

Posted in CNTK, Machine Learning | Leave a comment

Neural Regression using CNTK

I wrote an article titled “Neural Regression using CNTK” in the June issue of Microsoft MSDN Magazine. See https://msdn.microsoft.com/en-us/magazine/mt846729. The goal of a regression problem is to predict a single numeric value (such as the age of a person) — … Continue reading

Posted in CNTK, Machine Learning

A Quick Look at the Embedded Learning Library (ELL)

The Embedded Learning Library (ELL) is an open source project. The goal is to create a cross compiler for machine learning models. Briefly, machine learning models, such as those for image recognition, are typically very large in terms of memory. … Continue reading

Posted in CNTK, Machine Learning

The IMDB Movie Sentiment Analysis Problem using a CNTK LSTM Network

I successfully tackled the IMDB Movie Review dataset sentiment analysis problem. Coding up the system using the CNTK neural library was both easy and difficult — getting the data was difficult, writing the code was not as difficult as I’d … Continue reading

Posted in CNTK, Machine Learning

Free “Introduction to CNTK Succinctly” Book

I wrote a short book titled “Introduction to CNTK Succinctly” that you can get in PDF format for free. CNTK is an open source code library from Microsoft, which can be used to create deep neural network machine learning models. … Continue reading

Posted in CNTK, Machine Learning | 1 Comment

Installing CNTK v2.5 – What Could Possibly Go Wrong?

Microsoft CNTK is a code library for deep learning. Version 2.0 was a completely new library and first appeared in June 2017, about 9 months ago. Version 2.5 was released a few days ago so I decided to update my … Continue reading

Posted in CNTK, Machine Learning

Preparing Raw MNIST Data for use by a CNTK Program

The MNIST (“modified National Institute of Standards and Technology”) image dataset is often used to demonstrate image classification. The dataset has 60,000 images for training a model, and 10,000 images for evaluating a trained model. Each image is 28 pixels … Continue reading

Posted in CNTK, Machine Learning