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 | 47 | 6.44% |
Retrieval | 29 | 3.97% |
Semantic Segmentation | 28 | 3.84% |
Large Language Model | 23 | 3.15% |
Question Answering | 22 | 3.01% |
Object Detection | 15 | 2.05% |
Image Segmentation | 13 | 1.78% |
Image Classification | 11 | 1.51% |
Benchmarking | 11 | 1.51% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |