Hacker News new | ask | show | jobs
by freeone3000 2783 days ago
Oh, yep! It's super simple to induce systemic errors like that. Take https://github.com/kevin28520/My-TensorFlow-tutorials/tree/m... . Lighten every dog by 20%. Darken every cat by 20%. Train. Take image of cat, lighten 20%, watch as it's transformed into a dog!

For large corpora, it's impossible to know what features got selected. They probably aren't any feature a human would consider.