SCIENCE@home

Regularized Evolution for Image Classifier Architecture Search

Esteban Real,A. Aggarwal,Yanping Huang,Quoc V. Le

Published 2018 in AAAI Conference on Artificial Intelligence

ABSTRACT

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier— AmoebaNet-A—that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-theart 83.9% top-1 / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

LINKED PAPERS

CLAIMS

CONCEPTS

REFERENCES

Showing 1-88 of 88 references · Page 1 of 1

CITED BY

Showing 1-100 of 3251 citing papers · Page 1 of 33

123433
Next