NAS-RL

Reported on 3 benchmarks across 2 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Language ModellingonPenn Treebank (Word Level)
Test perplexity· 2016-11-05
64
best: 20.5 (GPT-3 (Zero-Shot))
SOTA
Neural Architecture Search with Reinforcement Learning arXiv:1611.01578
Language ModellingonPenn Treebank (Character Level)
Bit per Character (BPC)· 2016-11-05
1.214
best: 1.38 (Bipartite Flow)
Neural Architecture Search with Reinforcement Learning arXiv:1611.01578

Computer Vision1 result

Image ClassificationonCIFAR-10
Percentage correct· 2016-11-05
96.4
best: 99.5 (ViT-H/14)
Neural Architecture Search with Reinforcement Learning arXiv:1611.01578