Neural Architecture Search
Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.
Image Credit : NAS with Reinforcement Learning
Papers
Showing 1–10 of 1915 papers
All datasetsImageNetNAS-Bench-201, ImageNet-16-120CIFAR-10NAS-Bench-201, CIFAR-100NAS-Bench-201, CIFAR-10CIFAR-10 Image ClassificationCIFAR-100NATS-Bench Topology, CIFAR-10NATS-Bench Topology, CIFAR-100NATS-Bench Topology, ImageNet16-120Food-101NAS-Bench-101
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | EEEA-Net-C (b=5)+ CO | Params | 3.6 | — | Unverified |
| 2 | ENAS + c/o | Percentage error | 2.89 | — | Unverified |
| 3 | DARTS + c/o | Percentage error | 2.83 | — | Unverified |
| 4 | NAT-M1 | Percentage error | 2.6 | — | Unverified |
| 5 | GATES + c/o | Percentage error | 2.58 | — | Unverified |
| 6 | arch2vec | Percentage error | 2.56 | — | Unverified |
| 7 | Soft Parameter Sharing | Percentage error | 2.53 | — | Unverified |
| 8 | CATE | Percentage error | 2.46 | — | Unverified |
| 9 | NAS-RL-A + c/o | Percentage error | 2.4 | — | Unverified |
| 10 | PathLevel EAS + c/o | Percentage error | 2.3 | — | Unverified |