## Questions in this topic

- What does it mean if derivatives of parameters with respect to cost is negative?
- Is the line that separates y 0 and y 1 in a logistic function?
- Which of these is a benefit of batch normalization?
- What is the formula for calculating cost function?
- Can cost function be zero?
- What is S shaped curve?
- What is the cost function in machine learning?
- What is weight Ann?
- What is weight initialization neural network?
- What is Xavier initialization?
- Why batch normalization is used?
- Why does Xavier initialization work?
- Why is batch normalization important?
- Why is normalization important?
- Why is Softmax called Softmax?
- Why is Softmax used?
- Why we use sigmoid function in logistic regression?
- What is minimize cost?
- What is J in machine learning?
- What is hidden layer?
- Can I initialize a disk without losing data?
- Can loss function negative?
- Does it make sense to initialize all weights in a deep network to 0 justify?
- How do I find the hidden layer size?
- How do I initialize an unallocated disk?
- How does batch normalization help optimization?
- How does batch normalization work?
- How many hidden layers are there?
- Is NTFS MBR or GPT?
- What does Batch Norm do?
- What does sigmoidal curve mean?
- What does Softmax mean?
- What is disk initialization?
- What is dying ReLU?
- Will disk initialization erase data?