Feature detectors in early layers of neural networks detect simple features like edges (contrast between bright and dark regions), detected by having large positive weights for bright pixels and large negative weights for dark neighboring pixels, activating when one side is bright and the other dark
definitionpending
Speaker
Geoffrey HintonEvidence Quote
“a feature detector might have big positive weights to a column of pixels and then big negative weights to the neighboring column...if the column on one side is bright and the column on the other side is dim it'll get very excited and that's an edge detector”
Source
Possible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital— Joseph RaczynskiCreated: 8/10/2026, 10:48:51 PM
Your notes
Loading notes...