Lab 11: Multi Layer Perceptrons

1. A perceptron takes inputs, sums them, and produces an output based on a transfer function.
2. Make a perceptron with two inputs; use the pass through transfer function.
3. Make a linear transfer function, and set the slope to two.
4. Make weights for the inputs.
5. Now make two other perceptrons, with the same inputs, but different weights and slopes for the transfer function.
6. Do you see how one perceptron can duplicate the behaviour of 3.
7. Now make a different layer of three perceptrons.
8. Make the output from the first layer the input to the second.
9. Weight the connections.
10. Make a step transfer function.
11. Can you make an Xor Categoriser?