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 |
---|---|---|
GPT-4 | 97 | 11.62% |
Language Modelling | 46 | 5.51% |
Retrieval | 34 | 4.07% |
Semantic Segmentation | 27 | 3.23% |
Question Answering | 24 | 2.87% |
Large Language Model | 23 | 2.75% |
Object Detection | 18 | 2.16% |
Image Classification | 17 | 2.04% |
Text Generation | 12 | 1.44% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |