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:
$$ P(y=j \mid{x}) = \frac{e^{x^{T}w_{j}}}{\sum^{K}_{k=1}e^{x^{T}wk}} $$
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 43 | 5.77% |
Retrieval | 38 | 5.10% |
Question Answering | 29 | 3.89% |
Large Language Model | 23 | 3.09% |
Image Classification | 17 | 2.28% |
Semantic Segmentation | 17 | 2.28% |
Decoder | 16 | 2.15% |
Object Detection | 15 | 2.01% |
Text Generation | 13 | 1.74% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |