Recap of the 2017 DevIntersection Conference

I recently spoke at (and attended talks at) the 2017 DevIntersection Conference. The event was held October 29 to November 3, 2017, at the MGM Grand hotel in Las Vegas. There are actually several DevIntersection conferences every year, but the Vegas event is the original, and the one I never miss. See http://www.devintersection.com for details. […]

Continue reading


Making a Prediction from an MNIST Image Classification Model

I’ve been taking a deep look at the MNIST image classification problem. So far I wrote a utility function to convert the raw MNIST dataset images from their native binary format into text files. Then I used the CNTK code library to create a convolutional neural network prediction model. The MNIST dataset consists of 60,000 […]

Continue reading


The MNIST Image Classification Problem using CNTK

One of the standard deep learning problems is to classify the MNIST handwritten digits dataset. I took a deep dive into this problem, using the Microsoft CNTK deep learning code library. The MNIST dataset consists of 60,000 images used to create a prediction model. Each image is a handwritten digit, in 28-by-28 grayscale pixels. There […]

Continue reading