Output Functions

Softmax

The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$ and a weighting vector $w$ we have:

$$ P(y=j \mid{x}) = \frac{e^{x^{T}w_{j}}}{\sum^{K}_{k=1}e^{x^{T}wk}} $$

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Language Modelling 63 8.07%
Retrieval 31 3.97%
Large Language Model 31 3.97%
Question Answering 28 3.59%
In-Context Learning 24 3.07%
Sentence 19 2.43%
Object Detection 18 2.30%
Machine Translation 15 1.92%
Translation 14 1.79%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories