ML & AI for Software Developers - Part 5
Regression Modeling

When you build a machine-learning model, the first and most important decision you make is what learning algorithm to use to fit the model to the training data. In my previous post, I introduced some of the most widely used learning algorithms for regression models: linear regression, decision trees, random forests, gradient-boosting machines (GBMs), and…

ML & AI for Software Developers - Part 4
Regression Algorithms

Supervised-learning models come in two varieties: regression models and classification models. Regression models predict numeric outcomes, such as the price of a car. Classification models predict classes, such as the breed of a dog in a photo. When you build a machine-learning model, the first and most important decision you make is what learning algorithm…

ML & AI for Software Developers - Part 3
Supervised Learning with k-Nearest Neighbors

Most machine-learning models fall into one of two categories. Supervised-learning models make predictions. For example, they predict whether a credit-card transaction is fraudulent or a flight will arrive on time. Unsupervised-learning models don’t make predictions; they provide insights into existing data. The previous post in this series introduced unsupervised learning and used a popular algorithm…

ML & AI for Software Developers - Part 2
Unsupervised Learning with k-Means Clustering

Machine-learning models fall into two broad categories: supervised-learning models and unsupervised-learning models. The purpose of supervised learning is to make predictions. The purpose of unsupervised learning is to glean insights from existing data. One example of unsupervised learning is examining data regarding products purchased from your company and the customers who purchased them to determine…
Device In The Box

Project Santa Cruz Part 1: Unboxing and First Impressions

I started down the rabbit hole of AI a few years back when the idea of AI was coming to the forefront of computing rather than being relegated to a niche corner. I remember building my first AI models base on the MNIST dataset, which is often used as a benchmark for testing various classification…

Fundamentals of Deep Learning

Deep learning is a subset of machine learning that relies on deep neural networks. It is how computers identify objects in images, translate speech in real-time, generate artwork and music, and perform other tasks that would have been impossible just a few short years ago. Learn what neural networks are, how they work, and how…

Microsoft Custom Vision: Retrain Model in C#

In the previous post, we went over how to use the Custom Vision Training and Prediction SDKs to programmatically predict image URLs and image files. In this post, we’re going to use those same SDKs to show how to programmatically upload more training images to the service and train a new model with those new…

Microsoft Custom Vision: Creating an Image Classification Model

Creating a model to classify images would usually involve creating your own deep learning model from scratch. This includes having a very large and diverse set of training images with a portion of them set aside as a test set, a good convolutional neural network as the model, and a GPU enabled machine to do…

Microsoft Custom Vision: Predict Images with C#

In the previous post, we showed how to train an image classification model using the Microsoft Custom Vision service as well as to perform a quick test on a new image. However, what if you want to integrate this model into one of your applications that is using C#? Whether it’s an app that runs…

Wintellect Accepted Into the Microsoft AI Inner Circle Program

Wintellect is proud to have been selected as one of an elite group of invitation-only Microsoft partners to join Microsoft’s new AI Inner Circle Partner Program. “We are excited to be part of this exclusive group, and look forward to deepening our partnership with Microsoft and jointly advancing business transformations for our customers with AI,”…