Progressive Neural Architecture Search

Chenxi LiuBarret ZophMaxim NeumannJonathon ShlensWei HuaLi-Jia LiLi Fei-FeiAlan YuilleJonathan HuangKevin Murphy

   Papers with code   Abstract  PDF

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
2
PNASNet-5-Large
82.1%
--