Strange Loop

Machine learning failures - for art!

It's tough to write a machine learning algorithm that works well. Overfitting, noisy data, a problem that's too general - these problems plague the programmers who apply these algorithms to financial modeling and image labeling. But mistakes can also be fun. At her humor blog AIweirdness.com, Janelle Shane posts examples of machine learning algorithms going terribly, hilariously wrong. Here, she talks about some common machine learning mistakes - and how to use them deliberately.

Janelle Shane

Janelle Shane's neural network blog, AIweirdness.com, features computer programs that try to invent human things like recipes and paint colors and Halloween costumes. AIweirdness.com has been covered in the Guardian, the Atlantic, NBC News, Slate, All Things Considered, and more. Janelle also works as a research scientist in Colorado, where she makes computer-controlled holograms for studying the brain. She has only made a neural network recipe once and discovered that horseradish brownies are about as terrible as you might imagine.