lewisandquark:

I trained the neural network to generate superhero names, based on the list from this site.  I thought the database was going to be way too small, but the network proved me wrong.

Speet Stank
Red Fart
Mister Man
Rad Food
Sapgirl
Woop
Ann Man
Boomss
Boark II
Supperman
Superbore
Slonk
Lid Man
Green Hooter II
Starm Surper
Shartar
Goons
Nana
Rider Farm
Captain In
Redink
Wolver Man
Wizler

(via lewisandquark)

lewisandquark:

I trained the neural network to generate superhero names, based on the list from this site.  I thought the database was going to be way too small, but the network proved me wrong.

Speet Stank
Red Fart
Mister Man
Rad Food
Sapgirl
Woop
Ann Man
Boomss
Boark II
Supperman
Superbore
Slonk
Lid Man
Green Hooter II
Starm Surper
Shartar
Goons
Nana
Rider Farm
Captain In
Redink
Wolver Man
Wizler

(via lewisandquark)

lewisandquark:

I’m training a neural network to generate recipes based on a database of about 30,000 examples, and although it sometimes comes up with ingredients that sound like a bad idea, sometimes it invents some that you could plausibly ask for at Whole Foods and act all disappointed when they don’t have any:

¼ cup coconut fluff rings
1 teaspoon cooked buster grapes
½ cup shanked whipping peanuts
6 tablespoon lemon turn beans
1  seeds of the chocolate cheese
1 cup milk bat leaves
1 ½ cup sherry stick
¼ line phempherbly ice
½ cup shrimp white pine baking powder
1 teaspoon baking curny sauce
¼ cup milked salt
8 oz canned pomegranate crescents
12 oz can canned and chopped pistachio stock

(via lewisandquark)

lewisandquark:

This neural network, a learning algorithm trained on 30MB of cookbook recipes, generates new recipes based on probabilities. The resulting ingredients, while their words are individually probable, can end up disturbingly vague. “Yeah… I’m pretty sure this recipe’s gonna contain some… chunks.”

¼ cup white seeds
1 cup mixture
1 teaspoon juice
1  chunks
¼ lb fresh surface
¼ teaspoon brown leaves
½ cup with no noodles
1  round meat in bowl

(via lewisandquark)

lewisandquark:

As the neural network begins to get better at generating cookbook recipes, it continues to have trouble with recipe sources - short and highly varied, they’re a challenge for an algorithm that learns by repetition. Still, it does its best:

Source: Carrots
Shared By: Eander Moistly
Recipe By     : Berrand erroomsterplees
Recipe By     : Derned SAwaalcaima
Submitted by Alsalanne Mc.thebsete
Recipe By     : By LidienY Pubptite
Recipe by: Chef; Texigle The Steamy Fut 18
Cookies" cookbook by Herblen Leg 1994
by Pillian Cooking Broccoli
Source:  A dark Soup Cookbook by Searsh Leaves.
From Millryer Coancy First Warterrip Meltingonais
Source: Genter Marjary Witn Abong
Source: Cherry Sauce *  The Shell Bears Shelled Barbecue Sauce

(via lewisandquark)

lewisandquark:

I’m training a neural network to generate recipes based on a database of about 30,000 examples, and although the network has managed to produce identifiable recipes, and even sometimes sort sweet from savory, it hasn’t actually managed to produce any good ones. Only a very few of them are technically doable. Three typical examples:

Citran Barbecued Mube
game, ethnic      

—-CAKE—-
1 pkg cornstarch
34 oz ginger
1  white sage
2 large red potatoes, peeled
1  magazine bread; chunks
1 cup shredded corn peas
4 cup liquid ice cream

Preheat oven to 350 degrees. Remove the casserole from the refrigerator and heat soup for 20 min. Serve with nuts, chopped caczooled and serve with the rice and oatmeal.
From: Fial Hosselr                        Date: 24 Jul 96

Grilled Snailsed Butter
crockpot, vegetables, crockpot, rubbing holiday, meats

2 lb shrimp; cut in ½ cubes
6  cloves, minced
2 teaspoon apple juice
¼ cup mushrooms
1 lb tomatoes, nuts.  
plastic
1  Strawberries
2 each pinto beans; sliced
1  plum tomatoes, (no carri-fater)
1 pkg unknown yogurt fillets, thawed

Pour noodles and cauliflower through a wider measure just on high speed until stiff. Flavor radicchio mixture with the wine and continue simmering until mixture is desired doneness. Reserve side of bowl mixture. Chill until circle is reamy inricating. Serve on ranged removable pieces.

Smushed.I’s Bried, Heritame Sprigs
cakes, pies, pastries, extract

2  eggs
4 tablespoon water
1 cup dried butters and firmly beaten
20  eggs
4 oz fresh chopped nuts (approximately 10 minutes)
2 tablespoon grated zucchini
20 oz almonds, rough
1 cup seasoned baking powder

Sift milk in crockpot. Turn dough.

Add egg powdered sugar and whipped toppings. Serve immediately.

Posted by Adwing A

(via lewisandquark)

lewisandquark:

I’ve been training a neural network (based on this open-source neural network framework from Andrej Karpathy) to generate cookbook recipes. The results are … rarely delicious.

Some sample recipe titles:

Onion-Orange Brownies
Shredded Cheese Bananas
Monk Blebberra’s Crusted Carrots
Crockery Mist
Tamarind Bustard Beans
Choices Together Clam Lanting
Banana Washed
Hen Pan
Oven Meat
Chest Soup
Terofelbork
Berry Lerning Keef Pudding
Cheese Frinds
Sauce-Lavy’s Mustard Cookies
Snup Fruit: Bright Grilled Evaporated Milk
All-Foag-Day Cream
Masty Bacon
Philips Chicken With Upright Cheesecrumbs
Chocolate Spinach Prunes

Even more recipe titles here: http://lewisandquark.tumblr.com/post/140508739392/the-neural-network-has-weird-ideas-about-what

(via lewisandquark)

lewisandquark:

Neural networks are computer learning algorithms that mimic the interconnected neurons of a living brain, managing astonishing feats of image classification, speech recognition, or music generation by forming connections between simulated neurons.

I’m not a neural network researcher, but there’s never been a better time to experiment with them, thanks to open-source packages like torch, a scientific computing framework with built-in neural network capabilities. Inspired by Tom Brewe’s neural network-generated recipes, and enabled by the open-source torch add-on for character-based neural networks by Andrej Karpathy, I fired up the neural network code on my 2010 Macbook Pro, and started training it on a bunch of recipes I downloaded from a collection by David Shields.

Here’s a recipe my network has generated:

Pears Or To Garnestmeam

meats

¼ lb bones or fresh bread; optional
½ cup flour
1 teaspoon vinegar
¼ teaspoon lime juice
2  eggs

Brown salmon in oil. Add creamed meat and another deep mixture.

Discard filets. Discard head and turn into a nonstick spice. Pour 4 eggs onto clean a thin fat to sink halves.

Brush each with roast and refrigerate.  Lay tart in deep baking dish in chipec sweet body; cut oof with crosswise and onions.  Remove peas and place in a 4-dgg serving. Cover lightly with plastic wrap.  Chill in refrigerator until casseroles are tender and ridges done.  Serve immediately in sugar may be added 2 handles overginger or with boiling water until very cracker pudding is hot.

Yield: 4 servings

This is from a network that’s been trained for a relatively long time - starting from a complete unawareness of whether it’s looking at prose or code, English or Spanish, etc, it’s already got a lot of the vocabulary and structure worked out. 

This is particularly impressive given that it has the memory of a goldfish - it can only analyze 65 characters at a time, so by the time it begins the instructions, the recipe title has already passed out of its memory, and it has to guess what it’s making. It knows, though, to start by browning meat, to cover with plastic wrap before chilling in the refrigerator, and to finish by serving the dish.  

Compare that to a recipe generated by a much earlier version of the network:

Immediately Cares, Heavy Mim

upe, chips

3  dill loasted substetcant
1  cubed chopped  whipped cream
3  unpreased, stock; prepared; in season
1  oil
3 cup milk
1 ½ cup mOyzanel chopped
½ teaspoon lemon juice
1 ¼ teaspoon chili powder
2 tablespoon dijon stem – minced
30  dates afrester beater remaining

Bake until juice. Brush from the potato sauce: Lightly butter into the viscin. Cook combine water. Source: 0 25 seconds; transfer a madiun in orenge cinnamon with electres if the based, make drained off tala whili; or chicken to well. Sprinkle over skin greased with a boiling bowl.  Toast the bread spritkries.

Yield: 6 servings

which bakes first, has the source in the middle of the recipe directions, mixes sweet and savory, and doesn’t yet know that you can’t cube or chop whipped cream.

An even earlier version of the network hasn’t yet figured out how long an ingredients list should be; it just generates ingredients for pages and pages:

Tued Bick Car

apies

2 1/5 cup tomato whene intte
1 cup with (17 g cas pans or
½ cup simmer powder in patsorwe ½ tablespoon chansed in
1 ½ cup nunabes baste flour fite (115 leclic
2 tablespown bread to
¼ cup 12". oz mice
1  egg barte, chopped shrild end
2 cup olasto hote
¼ cup fite saucepon; peppen; cut defold
12 cup mestsentoly speeded boilly,, ( Hone
1  Live breseed
1  22 ozcugarlic
1 cup from woth a soup
4 teaspoon vinegar
2 9/2 tablespoon pepper garlic
2 tablespoon deatt
…

And here’s where it started out after only a few tens of iterations:

ooi eb d1ec Nahelrs  egv eael
ns   hi  es itmyer
aceneyom aelse aatrol a
ho i nr  do base
e2
o cm raipre l1o/r Sp degeedB
twis  e ee s vh nean  ios  iwr vp  e
sase  
pt e
i2h8
ePst   e na drea d epaesop
ee4seea .n anlp
o s1c1p  ,  e   tlsd
4upeehe
lwcc   eeta  p ri  bgl as eumilrt

Even this shows some progress compared to the random ASCII characters it started with - it’s already figured out that lower case letters predominate, and that there are lots of line breaks. Pretty impressive!

(via lewisandquark)

lewisandquark:

So I’ve been training this neural network to generate cookbook recipes by letting it look at tens of thousands of existing recipes.

The generated titles can get a bit odd.

There’s a creativity variable I can set when the network is generating new recipes, and when I set it low, it comes up with its best guess at the most quintessential recipe titles:

Cream Cheese Soup
Cream Of Sour Cream Cheese Soup
Chocolate Cake (Chocolate Cake)
Chocolate Chocolate Chocolate Cake
Chocolate Chicken Chicken Cake
Chocolate Chocolate Chocolate Chocolate Cake
Chocolate Chips
Chocolate Chips With Chocolate Chips

When I tell it to get creative, things get even weirder.

Beef Soup With Swamp Peef And Cheese
Chocolate Chops & Chocolate Chips
Crimm Grunk Garlic Cleas
Beasy Mist
Export Bean Spoons In Pie-Shell, Top If Spoon and Whip The Mustard
Chocolate Pickle Sauce
Whole Chicken Cookies
Salmon Beef Style Chicken Bottom
Star *
Cover Meats
Out Of Meat
Completely Meat Circle
Completely Meat Chocolate Pie
Cabbage Pot Cookies
Artichoke Gelatin Dogs
Crockpot Cold Water

(via lewisandquark)