According to Google, NASNet's performance exceeded all previously published Imagenet performance.
For example, around November 2017, Google's AutoML project to evolve new
neural net topologies created NASNet, a system optimized for Imagenet and COCO.
For example, around November 2017, Google's AutoML project to evolve new neural net topologies created NASNet,
a system optimized for Imagenet and COCO.
For example, around November 2017, Google's AutoML project to evolve new neural net topologies created NASNet,
a system optimized for Imagenet and POCO F1.
Facebook said,“The new technology will enable our researchers to scale themselves more quickly, and they are already using it to record
85.4 percent accuracy on the widely used‘Imagenet‘on benchmark.“.