What are the prerequisites for starting in deep learning?
What is a swish function?
What is a binary step function?
What do you understand by a convolutional neural network?
What is the most used activation function?
What are the disadvantages of deep learning?
In which layer softmax activation function used?
What are the supervised learning algorithms in deep learning?
What do you mean by dropout?
Do you think that deep network is better than a shallow one?
Explain the following variant of gradient descent: stochastic, batch, and mini-batch?
Explain the importance of lstm.
Why is zero initialization not a good weight initialization process?
What is matrix element-wise multiplication?
What do you understand by perceptron?