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 | 52 | 6.26% |
Retrieval | 39 | 4.69% |
Question Answering | 30 | 3.61% |
Large Language Model | 27 | 3.25% |
Semantic Segmentation | 25 | 3.01% |
Image Classification | 21 | 2.53% |
Decoder | 20 | 2.41% |
Object Detection | 16 | 1.93% |
Classification | 15 | 1.81% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |