"U Hack" and "Bog Love;" What happens when you train a neural network to write messages for Valentine's Day candy hearts

What happens when you train neural networks to write messages for candy hearts on Valentine's Day:

Here is Shane's original post:
 http://aiweirdness.com/ 
And here are links to the news coverage:
NPR
Popular Science
CNET
Bustle

For more on Shane's previous experiments on neural networks, read our story here:
When artificial intelligence is funny

This computer program really wants you to try strawberry ham pie this Thanskgiving

Still looking for a recipe idea for your Thanksgiving pie? Janelle Shane, who got her PhD in electrical engineering at the Jacobs School, is here to help--well, soft of.
Shane has trained a neural network, a type of computer program that learn by looking at examples, to generate recipe titles, based on a database of 2237 sweet and savory pie recipes.
The results didn't disappoint.
The neural network git creative and suggested Strawberry Ham Pie and Turkey Cinnamon Pie, as well as Impossible Maple Spinach Apple Pie--whatever that is.
Other suggestions were more on point, including Baked Cream Puff Cake, Eggnog Peach Pie and Fried Pumpkin Pie.
For more fun pie names and other neural network merriment, check out Shane's blog: http://aiweirdness.com/

So Bon Appetit! And Happy Thanksgiving!

Need a last-minute Halloween costume idea? This neural network has got you covered!

Need a last-minute costume idea for Halloween? How about a cyborg bat? Or a vampire shark? Or a magic sexy hamburger?
These are all costumes generated by a neural network trained by Jacobs School alumna Janelle Shane. Shane, who earned a Ph.D. in electrical engineering at UC San Diego in the lab of Professor Shaya Fainman, works with lasers by day. But her hobby is working with neural networks to create funny data sets.
For this project, she crowdsourced 4500 costume ideas from her blog readers and fed them to a neural network.
The network did not disappoint, generating costume suggestions such as vampire Big Bird, celery blue Frankenstein and strawberry shark.
Soon, Shane's readers were getting into the game and drawing the costumes the neural network suggested.
First up, strawberry shark:

And then: Bearley Quinn (courtesy of Twitter user @vonbees):

But Shane's readers weren't done. Soon they started making some of the costume suggestions a reality.
Twitter user Liz Walsh dressed up as the Dragon of Liberty:

Twitter user @HerbLovesTech and his wife dressed up as Professor Panda and Shark Princess:

And Shane? She took her inspiration from an entry in the costume data base. She will be Ruth Vader Ginsburg (that's a mash up of Supreme Court Justice Ruth Bader Ginsburg and Star Wars villain Darth Vader):

For more neural-network generated Halloween costumes, read Shane's blog post here. And read this news story by writer Rae Paoletta here and this Popular Mechanics story by writer Sophie Weiner.