2 gen 2016 anni - Barret Zoph and Quoc V Le.
Neural architecture search with
reinforcement learning,
arXiv 2016
Descrizione:
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.
Aggiunto al nastro di tempo:
Data:
~ 8 years and 4 months ago