Neural Architecture Search
Differentiable Architecture Search
Introduced by Liu et al. in DARTS: Differentiable Architecture SearchDifferentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with respect to its validation set performance through gradient descent.
Source: DARTS: Differentiable Architecture Search
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 14 | 12.61% |
| Reinforcement Learning (RL) | 6 | 5.41% |
| Test | 5 | 4.50% |
| Bilevel Optimization | 5 | 4.50% |
| Language Modelling | 5 | 4.50% |
| General Classification | 5 | 4.50% |
| Network Pruning | 4 | 3.60% |
| Classification | 4 | 3.60% |
| BIG-bench Machine Learning | 4 | 3.60% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
