Python - tensorflow.math.bessel_i1e() function

TensorFlow is open-source python library designed by Google to develop Machine Learning models and deep learning  neural networks. bessel_i1e() is function present in tensorflow math module. This function is used to find element wise exponentially scaled first order modified Bessel function.

Syntax: tensorflow.math.bessel_i1e(x, name)

Arguments:

• x: It's a tensor and the allowed dtypes for this tensor are bfloat16, half, float32, float64.
• name: It is an optional argument which is used to give operation name.

Returns: It returns a tensor or sparse tensor depending upon x of same dtype as x.

bessel_i1e(x) = exp(-abs(x)) bessel_i1(x)

bessel_i1e(x) is faster and numerically stabler than bessel_i1(x).

Example 1:

# importing the library
import tensorflow as tf

# initializing the input
a = tf.constant([1,2,3,4,5], dtype = tf.float64)

# printing the input 
print('a: ',a)

# evaluating the result
r = tf.math.bessel_i1e(a)

# printing the result
print("Result: ",r)

Output:

a:  tf.Tensor([1. 2. 3. 4. 5.], shape=(5,), dtype=float64)
Result:  tf.Tensor([0.20791042 0.21526929 0.19682671 0.17875084 0.16397227], shape=(5,), dtype=float64)

Example 2: Visualization

# importing the library
import tensorflow as tf
import matplotlib.pyplot as plt 

# initializing the input
a = tf.constant([1,2,3,4,5], dtype = tf.float64)

# evaluating the result
r = tf.math.bessel_i1e(a)

#plotting the graph
plt.plot(a, r, color = 'green', marker = "o")  
plt.title("tensorflow.math.bessel_i1e")  
plt.xlabel("Input")  
plt.ylabel("Result")  
plt.show() 

Output: