Representation Learning

A continuous vector encoding of an item (word, image, user) such that semantic similarity corresponds to geometric cl...

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data dis...

A continuous vector encoding of an item (word, image, user) such that semantic similarity corresponds to geometric cl...

When some classes are rare, requiring reweighting, resampling, or specialized metrics.

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained mod...

Training one model on multiple tasks simultaneously to improve generalization through shared structure.

Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.

A structured collection of examples used to train/evaluate models; quality, bias, and coverage often dominate outcomes.