papers AI Learner
The Github is limit! Click to go to the new site.

Evolutionary-Neural Hybrid Agents for Architecture Search

2019-01-24
Krzysztof Maziarz, Andrey Khorlin, Quentin de Laroussilhe, Stanisław Jastrzębski, Mingxing Tan, Andrea Gesmundo

Abstract

Neural Architecture Search has recently shown potential to automate the design of Neural Networks. The use of Neural Network agents trained with Reinforcement Learning can offer the possibility to learn complex architectural patterns, as well as the ability to explore a vast and compositional search space. On the other hand, evolutionary algorithms offer the sample efficiency needed for such a resource intensive application. We propose a class of Evolutionary-Neural hybrid agents (Evo-NAS), that retain the qualities of the two approaches. We show that the Evo-NAS agent outperforms both Neural and Evolutionary agents when applied to architecture search for a suite of text classification and image classification benchmarks. On a high-complexity architecture search space for image classification, the Evo-NAS agent surpasses the performance of commonly used agents with only 1/3 of the trials.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.09828

PDF

https://arxiv.org/pdf/1811.09828


Similar Posts

Comments