The Cat and the Bright Kitchen

Leggi questo articolo ad alta voce

Attiva il microfono e leggi con il tuo ritmo. Le parole si illuminano mentre procedi, e nulla ti ferma quando una viene pronunciata male.

Il tuo audio non arriva mai a MovaReader: a riconoscerlo è il tuo browser. Informativa sulla privacy

Accedi per conservare questa sessione nella cronologia delle letture.

The Cat and the Bright Kitchen

Nina wanted one pile of photos: every picture of her cat, Miso, and none of the empty rooms. The folder held years of shots, and she wanted an album from it. Writing a rule for every pose was hopeless. A cat can be a shadow on a sofa, a tail under a chair, or a face turned away. She turned to machine learning, which means the computer learns from examples instead of following a rule she writes for each case.

She labeled a stack of pictures by hand. Cat. Not a cat. Then she let a neural network train on them. A network like this is built in layers of small units, sometimes called neurons. Each link between units has a weight. When the network guessed wrong, those weights shifted a little, toward the label she had given.