Which of the following gives non-linearity to a neural network? (Choose only one)Stochastic Gradient DescentRectified Linear UnitConvolution function

You are training a neural network and you notice that the loss does not decrease in few epochs. The reasons for this could be: (Choose all the correct answers.)The learning rate is lowRegularization parameter is highStuck at local minimaVery deep architecture

What is the purpose of dropout in a neural network? (Choose all the correct answers.)To reduce the overall network sizeTo improve generalization over unseen dataTo reduce model overfitting on train dataTo increase the accuracy of the model

In the last layer of the network, when should one use sigmoid activation and when should one use softmax activation? (Choose only one.)Use sigmoid for getting increased accuracyUse sigmoid for multilabel classificationUse softmax for faster convergenceUsing softmax is theoretically sound

int i, j, k = 0;

for (i = n / 2; i <= n; i++) {

for (j = 2; j <= n; j = j * 2) {

k = k + n / 2;

}

}

What is the time complexity of the algorithm defined above? (choose only one)O(n)O(nlog(n))O(n^2)O(log(n))