Generative Models
Deep Belief Network
A Deep Belief Network (DBN) is a multi-layer generative graphical model. DBNs have bi-directional connections (RBM-type connections) on the top layer while the bottom layers only have top-down connections. They are trained using layerwise pre-training. Pre-training occurs by training the network component by component bottom up: treating the first two layers as an RBM and training, then treating the second layer and third layer as another RBM and training for those parameters.
Source: Origins of Deep Learning
Image Source: Wikipedia
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| General Classification | 18 | 17.82% |
| Image Classification | 9 | 8.91% |
| Time Series | 5 | 4.95% |
| Dimensionality Reduction | 5 | 4.95% |
| Denoising | 4 | 3.96% |
| Computer Vision | 4 | 3.96% |
| Speech Recognition | 4 | 3.96% |
| Object Recognition | 4 | 3.96% |
| Semantic Segmentation | 3 | 2.97% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
