I am new to neutral network & was trying to find derivative of sigmoid function.please help me to fix this error. My code is like;
import numpy as np
def sigmoid_derivative(x):
a=1/np.exp(x) +1
s=1/a
ds=s(1-s)
return ds
x = np.array([1, 2, 3])
print ("sigmoid_derivative(x) = " + str(sigmoid_derivative(x)))
Output:Error, numpy.ndarray is not callable.
on line ds=s(1-s)
you are calling numpy.ndarray s with parameter 1-s, I think you need ds=s * (1-s)
You're missing a multiplication operator:
ds= s * (1-s)
First of all, you got the sigmoid function wrong.
What I suggest is something like:
def sigmoid(x):
return 1.0 / (1.0 + np.exp(-x))
def sigmoid_derivative(x):
return sigmoid(x) * (1 - sigmoid(x))
Here's a link that would help you understand better: Derivative of the Sigmoid function
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.