Tweeted By @jeremyphoward

Anyone here familiar with the 'What do Deep Networks Like to See' paper? One of our students has noticed it seems to be making some odd conclusions based on checkerboard artifacts, but I haven't studied the paper closely enough to tell if this is an errorhttps://t.co/s4guQQ67nQ

— Jeremy Howard (@jeremyphoward) October 13, 2018