Janelle [MOVED] Shane

50 Followers
8 Following
14 Posts
[MOVED to @janellecshane]
I train neural networks to write humor at aiweirdness.com Also a research scientist in optics. she/her.
MOVED to @janellecshane
My local was speaking Japanese, so I'm going to hang out with scifi/fantasy folks. You seem nice.

Got a book sitting next to you?

Add its 1st sentence to this database so I can train a neural network to write the first sentence of a novel.

I'll run the experiment at the end of Nov.

https://docs.google.com/forms/d/e/1FAIpQLScod8P-kcLX98u6gT0rX6-20GwkDo_glz-okVVkrhr6KgQONQ/viewform

Write the first sentence of a novel - any novel. For science!

I train neural networks to write humor by giving them datasets that they have to mimic. You can check out my work at aiweirdness.com It’s National Novel Writing Month (NaNoWriMo, for short), which means that writers everywhere are embarking on writing projects - and when you’re faced with a blank page, sometimes it’s just hard to get started. A helpful neural network, which came up with a My Little Pony called Blue Cuss, a metal band called Chaosrug, and a craft beer called Yamquak, could save the day. But first, it needs to see lots of examples. Enter the first sentence of your novel, or your favorite novel, or of every novel on your bookshelf. Short stories/novellas etc okay too. You can enter as many as you like. At the end of the month, I’ll hopefully have enough sentences to try training a neural network. Want to be updated when I post new neural network content? You can sign up here: https://janelleshane.activehosted.com/f/1

This is why you shouldn't take cooking advice from a neural network.

http://lewisandquark.tumblr.com/post/159567612487/bad-recipe-ideas-from-the-neural-network

Bad recipe ideas from the neural network

I’m training a neural network to generate recipes based on a database of about 30,000 examples, using the open-source char-rnn framework. People have asked me whether I’ve tried making any of these recipes. The answer is no. No, I most definitely haven’t. I don’t know, in fact, of anyone who has dared. The following selections of ingredients and directions may help explain why. Ingredients/directions not recommended: 10 lb dried broccoli casserole 1 lb crab water ¼ oz can of fish casings Place wrapper in microwave on Low Coals. Mix honey, liquid  toe water, salt and 3 tablespoon olive oil. Cut flour into ¼-inch cubes Spread the butter in the refrigerator. Drop one greased pot. Remove part of skillet. Scrape the mold into a ball bowl. Ingredients/directions REALLY not recommended: 1 pkg unknown yogurt fillets, thawed 1  dark cream 3  cooked parts cut into chunks ½  ears, crumbled 1  binch wife ½ lb back of served ½ pint sharp pieces 2 tablespoon spore sauce 1  boneless head ham bananas 2 tablespoon minced fresh personn More: Bad ingredient ideas from the neural network Disturbingly vague ingredients from the neural network Bad cooking advice from the neural network It gets worse: Neural network recipes + neural network Lovecraft (Part 1) Neural network recipes + neural network Lovecraft (Part 2)

Tumblr

The neural network invents a cocktail of some sort.

Kodks. or Sugar Layer With Stock In Con Mublentchs

alcohol, cajun, dudes

2 pkg hershey’s can be prepared in unpeeled
1 smaller
½ cup yellow onions you may
1 cup egg; chilled, coursely chopped
½ lb bacon, chopped
1 ½ cup sugar, grated
4 oz square oil

Halve the finely chopped fresh garlic salt and pepper. Break the meat into the pinea..
More: http://lewisandquark.tumblr.com/post/159252246692/the-neural-network-designs-a-cocktail-of-some-sort

The neural network designs a cocktail of some sort

I’m training a neural network to generate recipes based on a database of about 30,000 examples, using the open-source char-rnn framework. I don’t remember there being alcoholic drinks in the original database, but apparently there were, because this happened: Kodks. or Sugar Layer With Stock In Con Mublentchs alcohol, cajun, dudes 2 pkg hershey’s can be prepared in unpeeled 1  smaller ½ cup yellow onions you may 1 cup egg; chilled, coursely chopped ½ lb bacon, chopped 1 ½ cup sugar, grated 4 oz square oil Halve the finely chopped fresh garlic salt and pepper. Break the meat into the pineapples and pat them, scraping the room off the skillet. Add ghees and beer and bring to a boil; cover and simmer, uncovered, on High for 20 to 30 minutes or until the onion thickens.  Remove from heat and stir in the soy sauce. Cook for about 3 minutes, adding a little about hot water and brown the meat. Add the mussels to the jar, blencard brieply and simmer until the potato vegetables are coarse through. Drain and serve would be required of the grated glaze and Wannational and cook in foam or water for 2-3 min. it using a fork.Create a little to two separate spaces fine and open. Yield: 4 servings

Tumblr

The neural network invents fruit variety names. Move over, Honeycrisp.

Brown Soften,
Ruby Wally,
Ruck,
Nagtort,
Blee Red,
Redcells,
Zuby Glong,
Zeelcher,
Hacker Gala,
Soften Fuji,
Klunk 134,
Horking,...

More:
http://lewisandquark.tumblr.com/post/159211716882/the-neural-network-invents-fruit-names-that-may

The neural network invents fruit names that may not catch on.

I’ve been training a neural network (based on this open-source neural network framework from Andrej Karpathy) on datasets from  recipes, to lists of Pokemon, to superhero names. I decided to see if it could invent names for new fruit varieties - I fed it a list of apple, peach, pear, plum, and cherry varieties, and asked it to generate more. It obliged. But I’m not sure any of these are going to catch on: Sunbrown Stanker Pork Gala Horspest Shivercell Hencough Moregall Brown Soften Ruby Wally Ruck Nagtort Blee Red Redcells Zuby Glong Zeelcher Hacker Gala Soften Fuji Klunk 134 Horking

Tumblr