Why is batch normalization important?

Related questions

1. What is hidden layer?
2. What is minimize cost?
3. What does Softmax mean?
4. What is weight Ann?
5. What is the cost function in machine learning?
6. Why is Softmax used?
7. How many hidden layers are there?
8. Does it make sense to initialize all weights in a deep network to 0 justify?
9. What is J in machine learning?
10. Why batch normalization is used?

Tags

1. #easier
2. #which
3. #using
4. #networks
5. #deeper
6. #batch
7. #initial
8. #weight
9. #helps
10. #especially
11. #difficult
12. #higher
13. #initialise
14. #initialisation
15. #weights
16. #creating
17. #speed
18. #starting
19. #allows
20. #learning
21. #train
22. #rates
23. #makes
24. #increasing
25. #reduce
26. #sensitivity
27. #normalisation