Output Functions

Edit

General • 10 methods

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

Add a Method

Method	Year	Papers
Softmax	2000	17914
Heatmap Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation	2014	297
Mixture of Logistic Distributions	2000	149
Adaptive Softmax Efficient softmax approximation for GPUs	2016	58
Sparsemax From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification	2016	21
EVM The Extreme Value Machine	2015	21
Hierarchical Softmax	2000	9
PAFs Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields	2016	6
Mixture of Softmaxes Breaking the Softmax Bottleneck: A High-Rank RNN Language Model	2017	3

Output Functions Edit

Methods Add a Method

Output Functions

Edit

Methods

Add a Method