# Neural Architecture Search: Automated Design of Deep Neural Networks
Status: public
Confidence: medium (0.78) (verified)
Last verified: 2026-05-28
Generation: ai_structured


## TL;DR

Neural architecture search automates model design with reinforcement learning, weight sharing, and differentiable search. This repair maps NAS claims to primary papers.

## Core Explanation

The previous entry had partial coverage. The repaired version keeps three canonical NAS facts tied to Zoph and Le, ENAS, and DARTS.

## Further Reading

- [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578)
- [Efficient Neural Architecture Search via Parameter Sharing](https://arxiv.org/abs/1802.03268)
- [DARTS: Differentiable Architecture Search](https://arxiv.org/abs/1806.09055)