Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic.... (more…)

Data cleaning, transfer learning, overfitting, ensembling, and more. (more…)

We're going to explore why the concept of vectors is so important in machine learning. We'll talk about how they are used to represent both data and models. ... (more…)

Google has released speed and efficiency comparisons between their TPU chip designed for deep learning applications and Nvidia's K80 and Intel's Haswell chips. The TPU crushed the competition. (more…)

You won't believe it, but you can run Machine learning on an Attiny85 (and many others Attiny). Not that you should, but you can. In this post I'll show you how! When I first run a Machine learning project on my Arduino Nano (old generation), it already f... (more…)