Derives a general relation between loss functions and t-norms that interprets cross-entropy and produces a novel class of losses for supervised learning.
In: Advances in Neural Information Processing Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the relation between Loss Functions and T-Norms
Derives a general relation between loss functions and t-norms that interprets cross-entropy and produces a novel class of losses for supervised learning.