Waymo & Google’s PolyLoss: Tailoring Loss Functions to Different Tasks and Datasets | Synced
Waymo and Google researchers’ new paper A Polynomial Expansion Perspective of Classification Loss Functions presents PolyLoss, a novel and simple framework that redesigns loss functions as a linear...
Source: Synced | AI Technology & Industry Review
Waymo and Google researchers’ new paper A Polynomial Expansion Perspective of Classification Loss Functions presents PolyLoss, a novel and simple framework that redesigns loss functions as a linear combination of polynomial functions that can be tailored to different target tasks and datasets.