I’m training a neural network to generate cookbook recipes. It looks at a bunch of recipes and has to figure out completely from scratch - no knowledge of what English words even are - how to start generating more recipes like them.

It has to start by figuring out which words are used in recipes. Here in a very early iteration, you can see the first somewhat intelligible word beginning to condense out of the network:

4 caam pruce 6 ½ Su ; cer
1 teaspoop
sabter fraze er intve
1 lep wonuu
s cap ter
3 tl spome. 2 teappoon terting peves, caare teatasing sad
ond le heed an ted pabe un Mlse; blacoins d cut ond ma eroy phispuz bambed
1 . teas, &

It’s trying SO hard to spell teaspoon. Teaspoop. It’s hilarious. It gets it right every once in a while, apparently by sheer luck, but mostly it’s:

ceaspoong, chappoon, conspean, deespoon, seaspooned, ceaspoon, tearpoon, teasoon, tertlespoon, teatpoon, teasposaslestoy, ndospoon, tuastoon, tbappoon, tabapoon, spouns, teappome, Geaspoon, leappoon, teampoon, tubrespoon…

It reeallly wants to learn to spell teaspoon. There are a lot of almost-teaspoons beginning with c… maybe it’s a mixture of teaspoon and cup. There are a few others that might be a tablespoon attempt.

Up next:
pupper, corm, bukter, cabbes, choped, vingr…

Subscribe now