why do we need data normalization?
Differentiate supervised and unsupervised deep learning procedures.
What do you mean by "overfitting"?
What is the use of the activation function?
What is tanh function?
What do you mean by deep learning?
Explain the different layers of cnn.
Which gpu is best for deep learning?
What is the most used activation function?
What do you understand by tensors?
Why is zero initialization not a good weight initialization process?
What are the prerequisites for starting in deep learning?
Are cuda cores important?
What is meant by deep learning?
What is the sigmoid function?