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 | 44 | 6.08% |
Retrieval | 33 | 4.56% |
Question Answering | 28 | 3.87% |
Large Language Model | 24 | 3.31% |
Semantic Segmentation | 21 | 2.90% |
Decoder | 21 | 2.90% |
Image Classification | 15 | 2.07% |
Classification | 14 | 1.93% |
Sentence | 12 | 1.66% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |