Why For loop is not preferred in Neural Network Problems?

For loop take much time for completing iterations and in ML practise we have to optimize the time so we can use for loops. But then you must be wondering what to use then? Don’t worry we will discuss this in the below section.

How to get rid from loop in Machine Learning or Neural Network?

The solution is Vectorization. Now the question arises what is vectorization? Vectorization is the process to convert algorithms from operating on a single value at a time to operate on a set of values (vector) at one time. Modern CPUs provide direct support for vector operations where a single instruction is applied to multiple data (SIMD).

Why to use Vectorization over for loop ?

Vectorization is used to speed up the Python code . Using np.function can help in minimizing the running time of code efficiently. Let’s see the below example for better understanding.






import numpy as np
import time
a = np.array([1, 2, 3, 4])
# there will be 100000 training data
a = np.random.rand(100000)
b = np.random.rand(100000)
# Measure current time
time1 = time.time()
# computing
c = np.dot(a, b)
# Measure current time
time2 = time.time()
# printing time taken for above calculation
print("vectorized form time taken"+ "\t"+str(1000*(time2-time1))+"ms")
# FOR for loop
# measure current time
time3 = time.time()
c = 0
# computing 
for i in range(100000):
  c+= a[i]*b[i]
# measure current time
time4 = time.time()
# printing time taken for above calculation
print("for loop time taken "+"\t\t"+str(1000*(time4-time3))+"ms")



vectorized form time taken    0.43511390686035156ms
for loop time taken         216.04394912719727ms
My Personal Notes arrow_drop_up

Check out this Author's contributed articles.

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.

Article Tags :


Please write to us at contribute@geeksforgeeks.org to report any issue with the above content.