COMP3411 Artificial Intelligence
Session 1, 2016

Week 11 Tutorial: Perceptrons, Neural Networks

1. Perceptron Learning
   1. Construct by hand a Perceptron which correctly classifies the following data; use your knowledge of plane geometry to choose appropriate values for the weights w₀, w₁ and w₂.

      Training Example	x1	x2	Class
      a.	0	1	-1
      b.	2	0	-1
      c.	1	1	+1

   2. Demonstrate the Perceptron Learning Algorithm on the above data, using a learning rate of 1.0 and initial weight values of

      w₀ = - 0.5
      w₁ = 0
      w₂ = 1

      In your answer, you should clearly indicate the new weight values at the end of each training step.

2. 18.21 Construct by hand a Neural Network (or Multi-Layer Perceptron) that computes the XOR function of two inputs. Make sure the connections, weights and biases of your network are clearly visible.

3. Explain how each of the following could be constructed:
   1. Perceptron to compute the OR function of m inputs
   2. Perceptron to compute the AND function of n inputs
   3. 2-Layer Neural Network to compute any (given) logical expression, assuming it is written in Conjunctive Normal Form.

4. (If time permits) Discuss how a neural network might be applied to each of the following tasks. For each task, describe how the inputs and outputs could be encoded, what network architecture and transfer function would be appropriate, what kind of pre- or post-processing might be helpful, and how the output of the network would be used within an overall system.
   1. playing tic-tac-toe
   2. recognizing postcodes written on letter envelopes
   3. predicting a person's risk of developing lung cancer, diabetes or heart disease
   4. making money on the stock market, or foreign currency exchange.

5. Any Questions about Assignment 3.