Category Archives: CNTK

Posts about the Microsoft CNTK deep learning code library

Iterating Through a CNTK-Format Data File

CNTK is Microsoft’s open source library for deep neural networks. A key component in CNTK code is a mini-batch object. A mini-batch object holds training data (input values and known correct output values) and a bunch of them are sent … Continue reading

Posted in CNTK, Machine Learning | 2 Comments

Implementing k-Means Clustering using Python

I’m investigating the possibility of writing code for k-means clustering using the CNTK library. CNTK was designed to create deep neural networks. But CNTK has low-level functions that in principle will allow me to write code for clustering. The idea … Continue reading

Posted in CNTK, Machine Learning | Leave a comment

Time Series Regression with an LSTM

Time series regression problems — predicting the next value in a sequence — look simple but are almost always extremely difficult. There are many different techniques you can use to tackle a time series regression problem. One of the newest … Continue reading

Posted in CNTK, Machine Learning | 1 Comment

Walking Through a CNTK Mini-Batch Object

CNTK is a powerful open source code library from Microsoft that can be used to create deep neural networks. A core object is a mini-batch — a collection of input values and known correct output values. You get a mini-batch … Continue reading

Posted in CNTK, Machine Learning

A First Look at ONNX

Open Neural Network Exchange Format (ONNX) version 1.0 was released on Wednesday, December 6, 2017. From what I can tell, ONNX is a specification standard for neural network models, so that different deep learning libraries can work together. According to … Continue reading

Posted in CNTK, Machine Learning

Writing CNTK Programs using the VS Code Editor

The Microsoft CNTK framework/library is a collection of powerful functions that you can use to write deep learning systems, for example, a deep neural network classifier. The most common way to use CNTK is to write a Python language program … Continue reading

Posted in CNTK, Machine Learning

LSTM Character Level Models and Sherlock Holmes

An LSTM network is an advanced, deep neural network system. LSTMs work well with sequences of words or characters because they have a memory. For example, if I ask you to predict the next two characters after “the do” you’d … Continue reading

Posted in CNTK, Machine Learning