Daniel Whitenack

Data scientist creating AI for good with SIL International. Co-host of the Practical AI podcast. Intel software innovator in ML/AI.

Read this first

AI building blocks - from scratch with Python

Linear regression and gradient descent are techniques that form the basis of many other, more complicated, ML/AI techniques (e.g., deep learning models). They are, thus, building blocks that all ML/AI engineers need to understand.


Regression is a process in which we model how one variable (for example, sales) changes with respect to another variable (for example, number of users). Generally, regression techniques in machine learning are concerned with predicting continuous values (for example, stock price, temperature, or disease progression). Classification, on the other hand, is concerned with predicting discrete variables, or one of a discrete set of categories (for example, fraud/not fraud, sitting/standing/running, or hot dog/not hot dog).

Linear regression, as you might expect, models the relationship a response (e.g., sales) and a feature (e.g., users) using the...

Continue reading →

Building a neural net from scratch in Go

I’m super pumped that my new book Machine Learning with Go is now available! Writing the book allowed me to get a complete view of the current state of machine learning in Go, and let’s just say that I’m pretty excited to see how the community growing!

In the book (and for my own edification), I decided that I would build a neural network from scratch in Go. Turns out, this is fairly easy, and I thought it would be great to share my little neural net here.

All the code and data shown below is available on GitHub.

(If you are interested in leveraging pre-existing Go packaging for machine learning, check out all the great existing packages, and be sure to watch Chris Benson’s recent talk at GolangUK about Deep Learning in Go)


There are a whole variety of ways to accomplish this task of building a neural net in Go, but I wanted to adhere to the following guidelines:

  • No cgo -...

Continue reading →