Introduction to Neural Networks for Java, Session 15

Session Material

Final Exam

(here is the final exam, it will be discussed next session)

1. When would you use the hyperbolic activation function over the sigmoid activation function?

2. Describe the structure the following network types: Hopfield, Self Organizing Map, Feedforward (2 hidden layers)?

3. Consider a feedforward neural network with 3 input neurons, 2 output neurons, and 2 hidden layers with 15 neurons each. How many matrixes, and what are their dimensions?

4. You would like to design a predictive feedforward neural network to attempt to predict the daily temperatures. You would like to use the past ten daily temperatures to predict tomorrow's temperature. How many input neurons, and what would you feed into them? How many output neuron(s), and what would you expect from it/them?

5. What is simulated annealing based on? Briefly describe how it works.

6. What happens if the backpropagation learning rate is too high? What happens if it is too low?

7. What is the difference between incremental and selective pruning.

8. You have a collection of insurance applications. You want to divide them into good, medium and low risk categories. Which type of neural network would you use? Why?

9. Is it valid to prune input or output layer neurons? Why so or why not?

10. What is the purpose of momentum in backpropagation? What does it seek to solve?

Videos for this Session

Video	Title
	Introduction to Neural Networks for Java(Class 15/16, Part 1/2)
	Introduction to Neural Networks for Java(Class 15/16, Part 2/2)