 Increase number of units in the hidden layer
 Increase number of hidden layers
 Increase data set size

Change activation function to tanh
 Try all of the above
The answer is d. When I use a linear activation function, the deep neural network is realizing a linear combination of linear functions which leads to modeling only a linear function. Increasing the depth or number of hidden units does not help. The network is not complex enough to learn a sine function and is underfitting the data. Change the linear function to tanh to realize a nonlinear decision boundary helps.