neural network design method
C28997
concept
A neural network design method is a systematic approach for selecting, structuring, and configuring neural network architectures and training procedures to solve specific computational or learning tasks.
Observed surface forms (7)
| Surface form | Occurrences |
|---|---|
| neural architecture search method | 3 |
| constructive neural network algorithm | 1 |
| convolutional neural network architecture family | 1 |
| differentiable architecture search algorithm | 1 |
| gradient-based optimization method for architectures | 1 |
| neural network training method | 1 |
| neuromorphic engineering approach | 1 |
Instances (7)
| Instance | Via concept surface |
|---|---|
| Neural Architecture Search | — |
| Cascade-Correlation learning architecture | neural network training method |
| analog VLSI for neural systems | neuromorphic engineering approach |
| NASNet | convolutional neural network architecture family |
| DARTS | neural architecture search method |
| ENAS | neural architecture search method |
| ProxylessNAS | neural architecture search method |