AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Avoid Collapse?
In contrastive running, you show two different images of the same object. You then train a network to produce an output representation e vactor a in such a way that those two images are as close to each other as possible. The idea was proposed by people at Belldabs and genbomley back in the early nineties. They were interested in storing a representation of the signature on 80 bites of the magnetic trip of a cretic card.