HIGHLIGHTS
SUMMARY
With the advancement in technology, the structure of modern machinery and equipment is becoming increasingly complex, meanwhile, the high requirements of reliability and increased precision must be met. Meta-learning aims at training a model based on a variety of learning tasks and adapting a new different but related task with very limited labeled data sample. The MAML is quite sensitive to neural_network structure and requires timeconsuming hyperparameters search to stabilize training and improve model generalization capability. In the hybrid model, the first several layers are the same as supervised learning, that is trained . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.