We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Multiclass 就是多分类问题,比如年龄预测中把人分为小孩,年轻人,青年人和老年人这四个类别
Multilabel 是多标签分类问题,比如一个新闻稿A可以与{政治,体育,自然}有关,就可以打上这三个标签。而新闻稿B可能只与其中的{体育,自然}相关,就只能打上这两个标签。
Multitask 是把多个相关(related)的任务放在一起学习,同时学习多个任务。比如,猫狗进行分类,可以按大小、颜色同时进行分类。 会涉及一个重要概念:共享表示shared representation (1)、基于参数的共享(Parameter based):比如基于神经网络的MTL,高斯处理过程。 (2)、基于约束的共享(regularization based):比如均值,联合特征(Joint feature)学习(创建一个常见的特征集合)。
原文链接:https://blog.csdn.net/lyly1995/article/details/92843908
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Multiclass
就是多分类问题,比如年龄预测中把人分为小孩,年轻人,青年人和老年人这四个类别
Multilabel
是多标签分类问题,比如一个新闻稿A可以与{政治,体育,自然}有关,就可以打上这三个标签。而新闻稿B可能只与其中的{体育,自然}相关,就只能打上这两个标签。
Multitask
是把多个相关(related)的任务放在一起学习,同时学习多个任务。比如,猫狗进行分类,可以按大小、颜色同时进行分类。
会涉及一个重要概念:共享表示shared representation
(1)、基于参数的共享(Parameter based):比如基于神经网络的MTL,高斯处理过程。
(2)、基于约束的共享(regularization based):比如均值,联合特征(Joint feature)学习(创建一个常见的特征集合)。
原文链接:https://blog.csdn.net/lyly1995/article/details/92843908
The text was updated successfully, but these errors were encountered: