Deep Learning
Representation Learning
Embeddings and transfer learning — reusing what networks already know
Embeddings
coreLearned dense vectors that place discrete things in a geometry where distance means similarity — the representation trick under NLP, recsys, and semantic search
9 minrepresentationembeddingsnlpTransfer learning and fine-tuning
coreReusing pretrained representations — when to freeze the backbone, when to fine-tune, and how to make 500 labeled examples go a very long way
10 minrepresentationtransfer-learningfine-tuning