Not only that but this process can continue retraining the selected NNs until some final parameter is reached (i. E. A low RMSE value) like a distillation process.

• 不仅仅是如此,而且这个过程可以持续训练所选的NNs直到得到某些最终的参数(例如一个较小的均方根差),就像是进行蒸馏。