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 1876–1900 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 | SPOS (ProxylessNAS (GPU) latency) | Accuracy | 75.3 | — | Unverified |
| 2 | SPOS (FBNet-C latency) | Accuracy | 75.1 | — | Unverified |
| 3 | SPOS (block search + channel search) | Accuracy | 74.7 | — | Unverified |
| 4 | MUXNet-xs | Top-1 Error Rate | 33.3 | — | Unverified |
| 5 | FBNetV2-F1 | Top-1 Error Rate | 31.7 | — | Unverified |
| 6 | LayerNAS-60M | Top-1 Error Rate | 31 | — | Unverified |
| 7 | NASGEP | Top-1 Error Rate | 29.51 | — | Unverified |
| 8 | MUXNet-s | Top-1 Error Rate | 28.4 | — | Unverified |
| 9 | NN-MASS-A | Top-1 Error Rate | 27.1 | — | Unverified |
| 10 | FBNetV2-F3 | Top-1 Error Rate | 26.8 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CR-LSO | Accuracy (Test) | 46.98 | — | Unverified |
| 2 | Shapley-NAS | Accuracy (Test) | 46.85 | — | Unverified |
| 3 | β-RDARTS-L2 | Accuracy (Test) | 46.71 | — | Unverified |
| 4 | β-SDARTS-RS | Accuracy (Test) | 46.71 | — | Unverified |
| 5 | ASE-NAS+ | Accuracy (Val) | 46.66 | — | Unverified |
| 6 | NAR | Accuracy (Test) | 46.66 | — | Unverified |
| 7 | BaLeNAS-TF | Accuracy (Test) | 46.54 | — | Unverified |
| 8 | AG-Net | Accuracy (Test) | 46.42 | — | Unverified |
| 9 | Local search | Accuracy (Test) | 46.38 | — | Unverified |
| 10 | NASBOT | Accuracy (Test) | 46.37 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Balanced Mixture | Accuracy (% ) | 91.55 | — | Unverified |
| 2 | GDAS | Top-1 Error Rate | 3.4 | — | Unverified |
| 3 | Bonsai-Net | Top-1 Error Rate | 3.35 | — | Unverified |
| 4 | Net2 (2) | Top-1 Error Rate | 3.3 | — | Unverified |
| 5 | μDARTS | Top-1 Error Rate | 3.28 | — | Unverified |
| 6 | NN-MASS- CIFAR-C | Top-1 Error Rate | 3.18 | — | Unverified |
| 7 | NN-MASS- CIFAR-A | Top-1 Error Rate | 3 | — | Unverified |
| 8 | DARTS (first order) | Top-1 Error Rate | 3 | — | Unverified |
| 9 | NASGEP | Top-1 Error Rate | 2.82 | — | Unverified |
| 10 | AlphaX-1 (cutout NASNet) | Top-1 Error Rate | 2.82 | — | Unverified |