Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Differentiable Neural Network Architecture Search
Richard Shin*, Charles Packer*, Dawn Song
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:The successes of deep learning in recent years has been fueled by the development
of innovative new neural network architectures. However, the design of a neural
network architecture remains a difficult problem, requiring significant human expertise
as well as computational resources. In this paper, we propose a method
for transforming a discrete neural network architecture space into a continuous
and differentiable form, which enables the use of standard gradient-based optimization
techniques for this problem, and allows us to learn the architecture and
the parameters simultaneously. We evaluate our methods on the Udacity steering
angle prediction dataset, and show that our method can discover architectures
with similar or better predictive accuracy but significantly fewer parameters and
smaller computational cost.
Enter your feedback below and we'll get back to you as soon as possible.