In this assignment, you will accomplish the following: 1. Modify an existing neural network model to improve performance 2. Explain how different approaches affect the performance of the model For the IMDB example that we discussed in class, do the following: 1. You used two hidden layers. Try using one or three hidden layers, and see how doing so affects validation and test accuracy. 2. Try using layers with more hidden units or fewer hidden units: 32 units, 64 units, and so on. 3. Try using the mse loss function instead of binary_crossentropy. 4. Try using the tanh activation (an activation that was popular in the early days of neural networks) instead of relu. 5. Use any technique we studied in class, and these include regularization, dropout, etc., to get your model to perform better on validation.Please solve this using R programming