Vincent Spruyt: Loc2 Vec: Self supervised metric learning through triplet loss

Selfsupervised learning is an increasingly popular technique to learn meaningful representations of data when no labels are available. A related problem is that of learning a mapping from raw input data into a metric space, where distances between latent data points are proportional to the semantic similarity between the original data instances. In this talk, we show how tripletloss can be used to train a neural network in a selfsupervised manner by applying it to location data. The result is a transform