Implement sigmoid function using Numpy

Implement sigmoid function using Numpy

Last Updated : 03 Oct, 2019

With the help of Sigmoid activation function, we are able to reduce the loss during the time of training because it eliminates the gradient problem in machine learning model while training.

Python3 1=1

# Import matplotlib, numpy and math
import matplotlib.pyplot as plt
import numpy as np
import math

x = np.linspace(-10, 10, 100)
z = 1/(1 + np.exp(-x))

plt.plot(x, z)
plt.xlabel("x")
plt.ylabel("Sigmoid(X)")

plt.show()

Output :

Example #1 :

Python3 1=1

# Import matplotlib, numpy and math
import matplotlib.pyplot as plt
import numpy as np
import math

x = np.linspace(-100, 100, 200)
z = 1/(1 + np.exp(-x))

plt.plot(x, z)
plt.xlabel("x")
plt.ylabel("Sigmoid(X)")

plt.show()

Output :

Implement sigmoid function using Numpy

J

jitender_1998

Improve

Article Tags :

Practice Tags :

python

Similar Reads

numpy.interp() function - Python

numpy.interp() function returns the one-dimensional piecewise linear interpolant to a function with given discrete data points (xp, fp), evaluated at x. Syntax : numpy.interp(x, xp, fp, left = None, right = None, period = None) Parameters : x : [array_like] The x-coordinates at which to evaluate the

Numpy matrix.I function | Python

With the help ofnumpy.matrix.I() function we can get the multiplicative inverse of the same size as of our given matrix. Syntax : numpy.matrix.I() Return : [matrix object] If self is non-singular, ret is such that ret * self == self * ret == np.matrix(np.eye(self[0, :].size) all return True. Return

numpy.nanstd() function - Python

numpy.nanstd() function compute the standard deviation along the specified axis, while ignoring NaNs. Syntax : numpy.nanstd(arr, axis = None, dtype = None, out = None, ddof = 0, keepdims) Parameters : arr : [array_like] Calculate the standard deviation of the non-NaN values. axis : [{int, tuple of i

numpy.i0() function | Python

numpy.i0() function is the modified Bessel function of the first kind, order 0. it's usually denoted by I0. Syntax : numpy.i0(x) Parameters : x : [array_like, dtype float or complex] Argument of the Bessel function. Return : [ndarray, shape = x.shape, dtype = x.dtype] The modified Bessel function ev

numpy.ma.masked_values() function | Python

numpy.ma.masked_values() function return a MaskedArray, masked where the data in array arr are approximately equal to value, determined using isclose. The default tolerances for masked_values are the same as those for isclose. Syntax : numpy.ma.masked_values(arr, value, rtol = 1e-05, atol = 1e-08, c