flâneur — a map of the web's best reading

Learning with not Enough Data Part 2: Active Learning

lilianweng.github.io · 4 words · saved by 1 readers

The performance of supervised learning tasks improves with more high-quality labels available. However, it is expensive to collect a large number of labeled samples. Active learning is one paradigm to deal with not enough labeled data, when there are resources for labeling more data samples but under a limited budget....

← Semi Supervised Learning

Explore this link on the map →

related reading