Methods › General › Output Functions

Output Functions

10 methods 38,029 papers tagged archive 2025-07-28

Output functions are layers used towards the end of a network to transform to the desired form for a loss function. For example, the softmax relies on logits to construct a conditional probability. Below you can find a continuously updating list of output functions.

Methods

All 10 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

Softmax – 37,443
Heatmap – 437
Mixture of Logistic Distributions – 170
Adaptive Softmax – 72
EVM Extreme Value Machine – 32
Sparsemax – 27
Hierarchical Softmax – 12
PAFs Part Affinity Fields – 6
Mixture of Softmaxes – 3
ADRM Adaptive Dynamic Recursive Mapping – 1