What is Xavier initialization?

Related questions

1. What is the formula for calculating cost function?
2. Why is Softmax used?
3. What does it mean if derivatives of parameters with respect to cost is negative?
4. Can I initialize a disk without losing data?
5. How does batch normalization help optimization?
6. What is hidden layer?
7. Why we use sigmoid function in logistic regression?
8. What does Batch Norm do?
9. How does batch normalization work?
10. What is weight Ann?

Tags

1. #neural
2. #originally
3. #networks
4. #yoshua
5. #difficulty
6. #feedforward
7. #xavier
8. #tries
9. #technique
10. #understanding
11. #bengio
12. #equal
13. #training
14. #outputs
15. #initialization
16. #variance
17. #proposed
18. #weights
19. #layer
20. #inputs
21. #glorot