2 янв 2016 г. - Barret Zoph and Quoc V Le. Neural architecture search with reinforcement learning, arXiv 2016
Описание:
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.Добавлено на ленту времени:
Дата:
2 янв 2016 г.
Сейчас
~ 8 гг и 5 мес назад
