5,332
edits
Deep Learning: Difference between revisions
→Domain Adaptation
| Line 1,507: | Line 1,507: | ||
#* I.e. <math>P(y|x) = Q(y|x)</math> | #* I.e. <math>P(y|x) = Q(y|x)</math> | ||
# Similarity of source and target marginal distributions. | # Similarity of source and target marginal distributions. | ||
# If I had labeled target samples, the | # If I had labeled target samples, the joint error (target + source samples) should be small. | ||
[Ben-David et al.] consider binary classification. | [Ben-David et al.] consider binary classification. | ||