Skip to Main Content
Python 机器学习实践:测试驱动的开发方法
book

Python 机器学习实践:测试驱动的开发方法

by Matthew Kirk
January 2018
Intermediate to advanced content levelIntermediate to advanced
211 pages
8h 31m
Chinese
China Machine Press
Content preview from Python 机器学习实践:测试驱动的开发方法
神经网络
135
激励函数
如上所述,激励函数(其中一些列在表
8-2
中)是在标准范围或对称范围之间规范化
数据的方式。它们也是有区别的,并且这种区别是有必要的,根据如何在训练算法中
决定权重,我们需要选用不同的激励函数。
8-2:激励函数
名称
标准的
对称的
Activation Functions
As mentioned, activation functions, some of which are listed in Table 8-2, serve as a
way to normalize data between either the standard or symmetric ranges. They also
are differentiable, and need to be, because of how we find weights in a training
algorithm.
Table 8-2. Activation functions
Name Standard Symmetric
Sigmoid
1
1+e
−2 · sum
2
1+e
−2 · sum
−1
Cosine
cos sum
2
+0.5
cos sum
Sine
sin sum
2
+0.5
sin sum
Gaussian
1
e
sum
2
2
e
sum
2
−1
Elliott
0.5·sum
1+ sum
+0.5
sum
1+ sum
Linear sum > 1 ? 1 : (sum < 0: sum) sum > 1 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Mastering Python for Bioinformatics

Mastering Python for Bioinformatics

Ken Youens-Clark

Publisher Resources

ISBN: 9787111581666