AutoML初步了解

               human automl

search space limited  exhaustive

 

 

proxy-based

step#1: define search space: conv cell

normal cell \ reduction cell

step#2:learn the optimal cell architecture for proxy task : CIFAR-10

step#3 : transfer the learned optimal architecture to target task: ImageNet

 

weight sharing-based approach

 

conclusion:

automl极大提高了生产效率：allows non-experts to solve ml problems

automl在很多AI任务上取得了比手动设计更好的性能（exceeds the world’s best ml experts ar many different tasks）

 

 

 

automl是否能构造出经典的模型结构？

由于automl先要define一个search space design，而这个define一般是借鉴经典模型，还是建立在已有经典模型上；