via
http://ift.tt/2zmDR9g:
lewisandquark:
It’s hard to come up with ideas for Halloween costumes, especially when it seems like all the good ones are taken. And don’t you hate showing up at a party only to discover that there’s *another* pajama cardinalfish?
I train neural networks, a type of machine learning algorithm, to write humor by giving them datasets that they have to teach themselves to mimic. They can sometimes do a surprisingly good job, coming up with a metal band called Chaosrug, a craft beer called Yamquak and another called The Fine Stranger (which now exists!), and a My Little Pony called Blue Cuss.
So, I wanted to find out if a neural network could help invent Halloween costumes. I couldn’t find a big enough dataset, so I crowdsourced it by asking readers to list awesome Halloween costumes. I got over 4,500 submissions.
The most popular submitted costumes are the classics (42 witches, 32 ghosts, 30 pirates, 22 Batmans, 21 cats (30 incl sexy cats), 19 vampires, and 17 each of pumpkins and sexy nurses). There are about 300 costumes with “sexy” in their names; some of the most eyebrow-raising include sexy anglerfish, sexy Dumbledore, sexy golden pheasant, sexy eyeball, sexy Mothra, Sexy poop emoji, Sexy Darth Vader, Sexy Ben Franklin, Sexy TARDIS, Sexy Cookie Monster, and Sexy DVORAK keyboard. In the “technical challenge” department, we have costumes like Invisible Pink Unicorn, Whale-frog, Glow Cloud, Lake Michigan, Toaster Oven, and Garnet.
All this is to say that humans are very creative, and this task was going to be tricky for a neural network. The sensible approach would be to try to use a neural network that actually knows what the words mean - there are such things, trained by reading, for example, all of Google News and figuring out which words are used in similar ways. There’s a fun demo of this here. It doesn’t have an entry for “Sexy_Gandalf” but for “sexy” it suggests “saucy” and “sassy”, and for “Gandalf” it suggests “Frodo”, “Gollum”, and “Voldemort”, so you could use this approach to go from “Sexy Gandalf” to “Sassy Voldemort”.
I wanted something a bit weirder. So, I used a neural network that learns words from scratch, letter by letter, with no knowledge of their meaning, an open-source char-rnn neural network written in Torch. I simply dumped the 4500 Halloween costumes on it, and told the neural network to figure it out.
Early in the training process, I decided to check in to see how it was doing.
Sexy sexy Dombie Sexy CatSexy A stare RowanSexy RoR A the RogSexy CotSexy Purbie LampirePoth RatSexy Por ManThe WombuePombie Con A A CatThe Ran Spean Sexy Sexy Pon Sexy DanderSexy CatThe Gull WotSexy PotHot
In retrospect, I should have expected this. With a dataset this varied, the words the neural network learns first are the most common ones.
I checked in a little later, and things had improved somewhat. (Omitted: numerous repetitions of “sexy nurse”). Still the only thing that makes sense is the word Sexy.
Sexy The Carding GingFarbat of the CowerSexy The HirlerA costumeSexy MenusSexy SureFrankenstein’s DenterA cardian of the PirateGing butterSexy the Girl Pirate
By the time I checked on the neural network again, it was not only better, but astoundingly good. I hadn’t expected this. But the neural network had found its niche: costume mashups. These are actually comprehensible, if a bit hard to explain:
Punk TreeDisco MonsterSpartan GandalfStarfleet SharkA masked boxMartian DevilPanda ClamPotato manShark CowSpace BatmanThe shark knightSnape ScarecrowGandalf the Good WitchProfessor PandaStrawberry sharkVampire big birdSamurai Angellady GarbagePirate firefighterFairy Batman
Other costumes were still a bit more random.
Aldonald the Goddess of the ChickenCelery Blue FrankensteinDancing BellyfishDragon of LibertyA shark princessStatue of WitchCupcake pantsBird ScientistGiant Two butterThe Twin Spider MermaidThe Game of Nightmare LightbareShare BatThe Rocky MonsterMario landerSpork SandStatue of pizzaThe Spiding hoodA card ConventionSailor PotterShower WitchThe Little PondSpice of pokemanBill of LibertyA spockCount Drunk Doll of PrincessPetty fairyPumpkin picardStatue of the Spice of the underworker
It still was fond of using made-up words, though. You’d be the only one at the party dressed as whatever these are.
SparraA masked scorby-babbersyScormboorMagic an of the foand tood-computerA barbanThe GumbkinScorbs MonsterA cat loory DuckThe BarboonFlatue doctorSparrow PlapperGrankensteinThe SpongebogMinional marty clownCount Vorror Rairol MencoonA neaving holdSexy Avical Ster of a balana AlyHuntle starber pirate
And it ended up producing a few like this.
Sports costumeSexy scare costumeGeneral Scare construct
The reason? Apparently someone decided to help out by entering an entire costume store’s inventory. (”What are you supposed to be?” “Oh, I’m Mens Deluxe IT Costume - Size Standard.”)
There were also some like this:
Rink Rater GinsburgA winged boxer GinsburgBed ridingh in a box Buther GinsburgSkeleton GinsburgZombie Fire Cith Bader Ginsburg
Because someone had entered about 50 variations on Ruth Bader Ginsberg puns (Ruth Tater Ginsberg, Sleuth Bader Ginsber, Rock Paper Ginsberg).
It invented some awesome new superheroes/supervillains.
Glow Wonder WomanThe BunnizerLadybogLight manBearley QuinnGlad womanrobot Werewolfsuper PunSuper of a bogSpace PantsBarferbuster pirateSkull Skywolk ladySkynation the GoddessFred of Lizard
And oh, the sexy costumes. Hundreds of sexy costumes, yet it never quite got the hang of it.
Sexy ScareSexy the PumpkinSaxy PumpkinsSexy the PirateSexy Pumpkin PirateSexy Gumb ManSexy barberSexy GarglesSexy humblebeeSexy The GateSexy LampSexy Ducty monsterSexy conchpaperSexy the BumbleSexy the Super bassPretty zombie Space Suitsexy DrangersSexy the Spock
You bet there are bonus names - and oh please go read them because they are so good and it was so hard to decide which ones to fit into the main article. Includes the poop jokes. You’re welcome.
I’ve posted the entire dataset as open-source on GitHub.
And you can contribute more costumes, for a possible future neural net upgrade (no email address necessary).
(Your picture was not posted)