Skip to content
New issue

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

stddev=np.sqrt(2 / (self.struct[-2] + self.struct[-1])) #9

Open
ghost opened this issue Jan 5, 2019 · 5 comments
Open

stddev=np.sqrt(2 / (self.struct[-2] + self.struct[-1])) #9

ghost opened this issue Jan 5, 2019 · 5 comments

Comments

@ghost
Copy link

ghost commented Jan 5, 2019

stddev=np.sqrt(2 / (self.struct[-2] + self.struct[-1])),stddev这个参数是标准差,我想2是不是应该是除数

@zhuofupan
Copy link
Owner

没错的,这是个经验式,二做除数的话这个标准差就很大了

@ghost
Copy link
Author

ghost commented Jan 5, 2019

谢谢,我在想那个DBN是怎么做迭代学习,强化模型。

@ghost
Copy link
Author

ghost commented Jan 5, 2019

你好,我想请问如何在原有的模型下,在新的训练数据下,继续强化学习。

@ghost
Copy link
Author

ghost commented Jan 5, 2019

这个改如何做

@zhuofupan
Copy link
Owner

强化学习没弄过,不太懂。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant