flâneur — a map of the web's best reading

Meta-Learning: Learning to Learn Fast

lilianweng.github.io · 11 words · saved by 2 readers

Meta-learning, also known as “learning to learn”, intends to design models that can learn new skills or adapt to new environments rapidly with a few training examples. There are three common approaches: 1) learn an efficient distance metric (metric-based); 2) use (recurrent) network with external or internal memory (model-based); 3)...

← Flow Based Deep Generative Models Object Detection Part 4 →

Explore this link on the map →

saved by

related reading