Neural Architecture Search

A topic within Deep Learning, itself one of 14 topics in that field and part of Artificial Intelligence.

Reading on Neural Architecture Search

2 works

Paper2017

Neural Architecture Search with Reinforcement Learning

Zoph & Le

Uses a recurrent network trained by reinforcement learning to generate the architecture description of a child network, using the child's validation accuracy as the reward — automating architecture design as a search problem rather than a design one.

16 pageslink checked 17 Sept 2026

Artificial Intelligence · Deep Learning

FreeAdvanced

Paper2018

DARTS: Differentiable Architecture Search

Liu, Simonyan & Yang

Relaxes the discrete choice of network operations into a continuous mixture that can be optimised by gradient descent alongside the network's weights, cutting the cost of architecture search from thousands of GPU-days to a handful.

13 pageslink checked 17 Sept 2026

Artificial Intelligence · Deep Learning

FreeAdvanced

Reading on Neural Architecture Search

Neural Architecture Search with Reinforcement Learning

DARTS: Differentiable Architecture Search

Other topics in Deep Learning