Zoph and Le: neural architecture search with reinforcement learning

What changed

Trained a controller to propose architectures and tested them on CIFAR-10 and Penn Treebank.

Scientific scope

The record is the exact two-author ICLR 2017 paper. It does not absorb later efficient neural-architecture-search methods, hardware-aware search, human engineering around the experiments or universal superiority claims.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact two-author ICLR 2017 paper. It does not absorb later efficient neural-architecture-search methods, hardware-aware search, human engineering around the experiments or universal superiority claims.

Contributors

• Barret Zoph · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Quoc V. Le · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Google Research record for neural architecture search

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction