Feedforward Networks
HyperNetwork
Introduced by Ha et al. in HyperNetworksA HyperNetwork is a network that generates weights for a main network. The behavior of the main network is the same with any usual neural network: it learns to map some raw inputs to their desired targets; whereas the hypernetwork takes a set of inputs that contain information about the structure of the weights and generates the weight for that layer.
Source: HyperNetworks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Federated Learning | 9 | 4.95% |
| Personalized Federated Learning | 8 | 4.40% |
| Multi-Task Learning | 8 | 4.40% |
| Reinforcement Learning (RL) | 7 | 3.85% |
| Meta-Learning | 7 | 3.85% |
| Super-Resolution | 6 | 3.30% |
| Few-Shot Learning | 6 | 3.30% |
| Continual Learning | 5 | 2.75% |
| Image Super-Resolution | 4 | 2.20% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
