Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output by a weight. This means there are $n_{\text{inputs}}*n_{\text{outputs}}$ parameters, which can lead to a lot of parameters for a sizeable network.
$$h_{l} = g\left(\textbf{W}^{T}h_{l-1}\right)$$
where $g$ is an activation function.
Image Source: Deep Learning by Goodfellow, Bengio and Courville
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 45 | 6.32% |
Retrieval | 33 | 4.63% |
Question Answering | 28 | 3.93% |
Large Language Model | 25 | 3.51% |
Decoder | 21 | 2.95% |
Semantic Segmentation | 20 | 2.81% |
Image Classification | 15 | 2.11% |
Classification | 12 | 1.69% |
Text Generation | 12 | 1.69% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |