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

神经网络动量因子 | 石锅拌饭 #17

Open
chunchengwei opened this issue Jan 23, 2019 · 0 comments
Open

神经网络动量因子 | 石锅拌饭 #17

chunchengwei opened this issue Jan 23, 2019 · 0 comments

Comments

@chunchengwei
Copy link
Owner

https://chunchengwei.github.io/ai/shen-jing-wang-luo-dong-liang-yin-zi/

反向传播算法中,学习率 $\eta$ 越小,每次迭代下降的步长越小,轨迹空间越平滑,学习速度越慢,提 $\eta$ 会加快学习速度,但网络权值的变化不稳定。为此,D.E. Rumlhart提出一种,既能加快学习速度,又能保持稳定的改进方法。

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

No branches or pull requests

1 participant