NASNet
A neural network architecture discovered by Google Brain using neural architecture search. NASNet is an early representative result in the NAS field and required hundreds of GPUs running for thousands of hours to complete the search process.
Timeline (last 90 days)
Google Brain's NASNet required running on hundreds of GPUs for thousands of hours to find an architecture that performed well on specific tasks.
Early NAS work (such as NASNet and DARTS) was found, due to opaque search space design, to have discovered architectures that largely depended on specific proxy tasks and search budgets.
Google在2017年提出的NASNet架构由AI通过神经架构搜索自动发现，在图像分类任务上性能超越许多人类设计的架构
All Facts (3)
Google Brain's NASNet required running on hundreds of GPUs for thousands of hours to find an architecture that performed well on specific tasks.
50%UnverifiedEarly NAS work (such as NASNet and DARTS) was found, due to opaque search space design, to have discovered architectures that largely depended on specific proxy tasks and search budgets.
50%UnverifiedGoogle在2017年提出的NASNet架构由AI通过神经架构搜索自动发现，在图像分类任务上性能超越许多人类设计的架构
50%