Progressive Neural Architecture Search

被引：1017

作者：

Liu, Chenxi ^{[1
]}

Zoph, Barret ^{[2
]}

Neumann, Maxim ^{[2
]}

Shlens, Jonathon ^{[2
]}

Hua, Wei ^{[2
]}

Li, Li-Jia ^{[2
]}

Li Fei-Fei ^{[2
,3
]}

Yuille, Alan ^{[1
]}

Huang, Jonathan ^{[2
]}

Murphy, Kevin ^{[2
]}

机构：

[1] Johns Hopkins Univ, Baltimore, MD 21205 USA

[2] Google AI, Mountain View, CA USA

[3] Stanford Univ, Stanford, CA 94305 USA

来源：

COMPUTER VISION - ECCV 2018, PT I | 2018年 / 11205卷

关键词：

D O I：

10.1007/978-3-030-01246-5_2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of number of models evaluated, and 8 times faster in terms of total compute. The structures we discover in this way achieve state of the art classification accuracies on CIFAR-10 and ImageNet.

引用

页码：19 / 35

页数：17