Microsoft CNTK v2 is an extremely powerful code library you can use to create deep machine learning prediction models. In this informal in-depth presentation, Dr. James McCaffrey from Microsoft Research will explain exactly what CNTK is, and describe the types of problems CNTK can and can't solve. You will leave this presentation with all the information you need to create a working deep neural prediction system. This session will cover installing CNTK, the CTF data file format and data readers, creating deep neural network layers, understanding squared error vs. log loss, training with advanced stochastic gradient descent, model evaluation, and transferring a CNTK model to a C# program.

You will learn:

• Exactly what CNTK can and cannot do
• How to create a deep neural prediction system using CNTK
• How to transfer a CNTK model to a C# program