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 | 59 | 7.78% |
| Image Classification | 25 | 3.30% |
| Semantic Segmentation | 25 | 3.30% |
| Question Answering | 22 | 2.90% |
| Text Generation | 21 | 2.77% |
| Object Detection | 21 | 2.77% |
| Self-Supervised Learning | 19 | 2.51% |
| reinforcement Learning | 15 | 1.98% |
| Machine Translation | 14 | 1.85% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
