Whiskeridoo! AI named these adorable, adoptable kittens

Whiskeridoo! AI named these adorable, adoptable kittens

[ad_1]

morriscats

Tom Glitter and Sparky Buttons owe their cute names to a neural network.


Morris Animal Refuge

Sparky Buttons has eye damage from a infection he caught when he was a stray baby, but he’s still a powerhouse when it comes to cuddling and playing. And don’t be fooled by Mr. Sinister’s name. He’s a cuddler, too. 

These adoptable kittens, along with their friends Tom Glitter, Pompompur and Whiskeridoo, were all named by an artificial intelligence neural network. 

The Morris Animal Refuge in Philadelphia teamed up with research scientist Janelle Shane. Shane trained a neural network to name cats, and the results are cute, weird and sometimes downright horrible. 

She originally trained a network by giving it 8,000 cat names to learn from, but the AI stumbled, giving out names like Hurler and Retchion. Shane revisited the challenge with an AI that had a lot more context and trained it up with a long list of cat names. This time around, it was (somewhat) more successful.

The neural net suggested adorable names like “Notion,” “Monocle” and “M. Tinklesby Linklater Soap.” Sometimes it went south with ideas like “Scat Cat Butthole,” “Fudge Putty” and “BUTT.” On occasion, it hinted at a dark turn of thought with “Warning Signs,” “Bones of the Master” and “Kill All Humans.” You can read a more complete list on Shane’s site.

Shane has become the go-to person for entertaining neural net names. She previously trained AI systems to come up with cookie names (Hallowy Maples, Apricot Dream Moles) and D&D monsters (Spectral Slug, Jabberwont).

The Morris Animal Refuge had previously embraced neural net names for guinea pigs and it hopes the kittens and cats will get an adoption boost from their fun and fanciful AI monikers. 

It seems to be working. Mr. Sinister has been adopted, Morris Animal Refuge announced on Monday.  



[ad_2]

READ MORE HERE

Leave a Reply

Your email address will not be published.