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 | 60 | 7.72% |
Retrieval | 31 | 3.99% |
Large Language Model | 30 | 3.86% |
Question Answering | 29 | 3.73% |
In-Context Learning | 22 | 2.83% |
Sentence | 19 | 2.45% |
Machine Translation | 15 | 1.93% |
Translation | 15 | 1.93% |
Object Detection | 14 | 1.80% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |