2 Jan 2016 Jahr - Barret Zoph and Quoc V Le.
Neural architecture search with
reinforcement learning,
arXiv 2016
Beschreibung:
It first proposes to use reinforcement learning to generate neural network architectures with high accuracy and efficiency. However, the proposed method requires huge amounts of computing resources.
Zugefügt zum Band der Zeit:
Datum:
~ 8 years and 5 months ago