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…Tell this neural network I love it
mildly disappointed by the lack of a “my name is netwerk” poem in the reblogs
i am netwerk
and wen im taut
the recipes
that cooks hav goti trie my best
ill get it soon
in the meentimei spel the spouns
aaaaa excellent, all is now right with the world