In her spare time, University of California, San Diego engineer Janelle Shane trained a neural network to generate recipes for new dishes. Informed by its reading of existing recipes, the neural network did improve over time yet it’s clearly not quite ready for Iron Chef. Here are two recipes from her Tumblr, Postcards from the Frontiers of Science:
Pears Or To Garnestmeam
meats
¼ lb bones or fresh bread; optional
½ cup flour
1 teaspoon vinegar
¼ teaspoon lime juice
2 eggsBrown 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 remainingBake 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.
“The Silicon Gourmet: training a neural network to generate cooking recipes” (Thanks, Toshi Hoo!)