torch*

The neural network has weird ideas about what humans like to eat

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

The neural network doesn’t understand pepper.

As the neural network tries to learn to generate recipes by looking at a 30MB cookbook, there are certain ingredients it has to learn to deal with.  One of the most confusing for the network is pepper.

In retrospect, that makes some sense - it’s looking at example recipes that have 1 teaspoon black pepper, ¼ teaspoon ground pepper, 1 pinch white pepper, a dash cayenne pepper, 1 cup green pepper, etc, so it makes the leap that pepper must come in the form of 

Quantity + unit_of_measure + word + pepper.  

It’s having a hard time figuring out the acceptable list of words that come before pepper. So far we’ve got:

½ teaspoon rusting pepper
½ teaspoon dried caramel pepper
½ cup cooked beef pepper
1 tablespoon crompwed pepper
1 ½ teaspoon draining pepper
½ teaspoon lame pepper
1 cup corndrain pepper
½ teaspoon drees pepper
1 single baning pepper
1 teaspoon dark pepper
½ teaspoon dried pepper
¼ teaspoon fangly chopped pepper

The neural network gives bad cooking advice

I’ve trained the neural network on about 30MB of cookbook recipes, but its cooking advice still doesn’t seem that great.

I’m not sure I should do or add any of these things.

1 cup cherry seeds
42 cup milk
Preheat oven to 3500  8 minutes.
beat until the gelatins are firm.
Brown egg yolks until smooth.
Fold water. Roll into small cubes.
Fill the egg with a spatula.
1 cup meat or flour
5 ½ to 10 small centers of green bell peppers
Sprout clams; add vanilla.