Feedforward Networks
Dense Connections
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
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 49 | 6.34% |
| Retrieval | 35 | 4.53% |
| Semantic Segmentation | 29 | 3.75% |
| Question Answering | 28 | 3.62% |
| Large Language Model | 24 | 3.10% |
| Object Detection | 13 | 1.68% |
| Image Segmentation | 13 | 1.68% |
| In-Context Learning | 13 | 1.68% |
| Sentence | 12 | 1.55% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
