A (Nearly) Stats-Free Adventure — Whether you’re a practicing data scientist or a budding data student, you’re probably familiar with the bias-variance tradeoff. It’s an essential factor in model type selection, right up there with the accuracy-explainability tradeoff. But, how well do you understand it on an intuitive level? If you’re anything like I was…

How a Statistician Reacts to Life on Venus — If you’re the sort of person who reads data science blogs (well hello there!) then you probably already know about Bayes’ Law. Heck, you’ve probably even used it yourself. Unfortunately, in my experience, many people only know Bayes’ Law in a technical, academic context, and don’t actually understand it in…

A Jump-Start GAN Tutorial — In this tutorial, we’ll be building a simple DCGAN in PyTorch and training it to generate handwritten digits. As part of this tutorial we’ll be discussing the PyTorch DataLoader and how to use it to feed real image data into a PyTorch neural network for training. …

Building the Simplest of GANs in PyTorch — I spent a long time making GANs in TensorFlow/Keras. Too long, honestly, because change is hard. It took some convincing, but I eventually bit the bullet and swapped over to PyTorch. Unfortunately, most of the PyTorch GAN tutorials I’ve come across were overly-complex, focused more on GAN theory than application…

How the AEGAN architecture stabilizes GAN training and prevents mode collapse — GANs are hard to train. When they work, they work wonders, but anyone who’s tried to train one themselves knows they’re damn finicky bastards. Two of the most common problems in GAN training are mode collapse and lack of convergence. In mode collapse, the generator learns to only generate a…

and other dead-giveaways that you’re a fake data scientist — These days it seems like everyone and their dog are marketing themselves as data scientists—and you can hardly blame them, with “data scientist” being declared the Sexiest Job of the Century and carrying the salary to boot. Still, blame them we will, since many of these posers grift their way…

Visualizing how GANs learn in low-dimensional latent spaces — Generative Adversarial Networks (GANs) are a tool for generating new, “fake” samples given a set of old, “real” samples. These samples can be practically anything: hand-drawn digits, photographs of faces, expressionist paintings, you name it. To do this, GANs learn the underlying distribution behind the original dataset. Throughout training, the…

How GANs tie themselves in knots and why that impairs both training and quality — A warning to mobile users: this article has some chunky gifs in it. Generative Adversarial Networks (GANs) are being hailed as the Next Big Thing™️ in generative art, and with good reason. New technology has always been a driving factor in art — from the invention of paints to the…

Visualizing the Very Basics of Generative Adversarial Networks — In the original Generative Adversarial Network paper, Ian Goodfellow describes a simple GAN which, when trained, is able to generate samples indiscernible from those sampled from the normal distribution. This process is illustrated here: The simplest solution for this task is for the GAN to approximate the inverse CDF of…