Due on April 4

1. (10 points) Estimate the MSFT stock price again with a fully connected neural network with 5 hidden layers. Each hidden layers have 20 neurons. And use ReLU as activation function.

2. (2 points) Plot the training loss vs epoch.

3. (4 points) Add dropout to networks and train again. Also plot the training loss vs epoch.

4. (2 points) Plot the predicted MSFT price (with and without dropout) for the training data. In the same plot, please include the ground truth and the predicted price by SVR and linear regression from earlier HW.

5. (2 points) Create the same plot above for the test data.

You can use any neural network packages. I would recommend PyTorch though.