Does it make sense to initialize all weights in a deep network to 0 justify?

Related questions

1. What is weight Ann?
2. What is J in machine learning?
3. How do I initialize an unallocated disk?
4. Can loss function negative?
5. What does sigmoidal curve mean?
6. Can I initialize a disk without losing data?
7. Why is Softmax used?
8. Why we use sigmoid function in logistic regression?
9. Why is Softmax called Softmax?
10. What does Softmax mean?

Tags

1. #function
2. #initializing
3. #every
4. #respect
5. #derivative
6. #iterations
7. #symmetric
8. #continues
9. #makes
10. #values
11. #weights
12. #iteration
13. #subsequent
14. #hidden
15. #weight
16. #units