• l.cristian

Few shot learning with Triplet Loss

This video is a sample of the materials covered in our Deep Learning (II) module.


In it you can see an established technique for solving inverted classification problems, also called few-shot-learning problems.


It revolves around using a Siamese Network and a custom loss function called Triplet Loss to learn a distance metric between pairs of examples.



38 views0 comments

Recent Posts

See All