- 专利标题： Self-training method and system for semi-supervised learning with generative adversarial networks
-
申请号： US15789628申请日： 2017-10-20
-
公开(公告)号： US11120337B2公开(公告)日： 2021-09-14
- 发明人: Dalei Wu , Md Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri
- 申请人： Dalei Wu , Md Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri
- 申请人地址： CA St. Laurent; CA Montreal; CA Montreal; CA St. Laurent
- 专利权人： Dalei Wu,Md Akmal Haidar,Mehdi Rezagholizadeh,Alan Do-Omri
- 当前专利权人： Dalei Wu,Md Akmal Haidar,Mehdi Rezagholizadeh,Alan Do-Omri
- 当前专利权人地址： CA St. Laurent; CA Montreal; CA Montreal; CA St. Laurent
- 主分类号： G06N3/04
- IPC分类号： G06N3/04 ; G06N3/08
摘要：
A method and system for augmenting a training dataset for a generative adversarial network (GAN). The training dataset includes labelled data samples and unlabelled data samples. The method includes: receiving generated samples generated using a first neural network of the GAN and the unlabelled samples of training dataset; determining a decision value for a sample from a decision function, wherein the sample is a generated sample of the generated samples or an unlabelled sample of the unlabelled samples of the training dataset; comparing the decision value to a threshold; in response to determining that the decision value exceeds the threshold: predicting a label for a sample; assigning the label to the sample; and augmenting the training dataset to include the sample with the assigned label as a labelled sample.
公开/授权文献
信息查询
