AI Weirdness: the strange side of machine learning

Tag: BigGAN

Total 8 Posts
Curse your valentine with these candy hearts

Curse your valentine with these candy hearts

When I’ve generated candy heart messages before, they’ve been text only - definitely some assembly required. But methods of generating custom images from descriptions are getting better all the time. Could I use modern machine learning to generate new candy hearts? The answer is no. For the image
Searching for Bernie

Searching for Bernie

“Leaning Tower of Pizza”, BigGAN steered by CLIP using Big SleepI wrote earlier about DALL-E, an image generating algorithm recently developed by OpenAI. One part of DALL-E’s success is another algorithm called CLIP, which is essentially an art critic. Show CLIP a picture and a phrase, and it’ll
When data is messy

When data is messy

There’s a story I tell in my book because it’s a great illustration of how AI gets the wrong idea about what problem we’re asking it to solve: Researchers at the University of Tuebingen trained a neural net to recognize images, and then had it point out
A weirdly broken AI

A weirdly broken AI

The other day someone told me about a program that will generate scenes to match a text description. I’m always excited to test out algorithms like this because the task of “draw anything a human asks for” is so hard that even state-of-the-art results are hilariously bad. I tried
What is the opposite of guacamole?

What is the opposite of guacamole?

Last week I attempted to illustrate some neural net-generated racehorses by turning to another neural net - this time, one that generates images, called BigGAN. Using Joel Simon’s ganbreeder.app interface, I’m able to see what BigGAN can generate for any of ~1000 categories of objects. Not finding
Welcome to Latent Space

Welcome to Latent Space

I’ve written before about BigGAN, an image-generating neural net that Google trained recently. It generates its best images for each of the 1,000 different categories in the standard ImageNet dataset, from goldfish to planetarium to toilet tissue. And the images it produces are both beautifully textured and deeply
The creepiest images generated by BigGAN

The creepiest images generated by BigGAN

Writing to you from deep inside the Uncanny Valley, I present to you some hand-selected images generated by an algorithm called BigGAN. This algorithm looks at example images of a bunch of different objects and then tries its best to figure out how to generate more of them. Because the
Imaginary worlds dreamed by BigGAN

Imaginary worlds dreamed by BigGAN

These are some of the most amazing generated images I’ve ever seen. Introducing BigGAN, a neural network that generates high-resolution, sometimes photorealistic, imitations of photos it’s seen. None of the images below are real - they’re all generated by BigGAN. Preprints of the BigGAN paper are here
You've successfully subscribed to AI Weirdness
Great! Next, complete checkout for full access to AI Weirdness
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.