factual
Adversarial examples show deep networks use non-human statistical shortcuts
Moitra argues that deep networks solve object recognition through statistical relationships humans do not use, shown by adversarial patterns that fool detectors and by experiments where networks trained on mislabeled adversarial data still generalize to natural data, so AI success is not human-like.
factualpending
Speaker
Ankur MoitraEvidence Quote
“when you train a deep network on this with all the wrong labels, it's gonna learn something that does well on natural data”
Created: 11/17/2026, 6:25:32 AM
Your notes
Loading notes...