CS322 Fall 1999
Module 12 (Neural Network Learning)

Assignment 12

Due: 1:30pm, Friday 3 December 1999.

Question 1

The following is the same data from assignment 11:
Example bought edu first visited more_info
e1 false true false false true
e2 true false true false false
e3 false false true true true
e4 false false true false false
e5 false false false true false
e6 true false false true true
e7 true false false false true
e8 false true true true false
e9 false true true false false
e10 true true true false true
e11 true true false true true
e12 false false false false true
We want to use this data to learn the value of more_info as a function of the values of the other variables.

In this assignment we will consider neural network learning for this data. We have a Java applet and a CILog program that can be used to answer this assignment.

  1. Consider neural network learning with no hidden layers. After the network has converged, what are the parameter values? What is the Boolean function that the network represents? Are all the training examples classified correctly (if not, which aren't)? Give two examples, not in the training set, and specify what the predicted values is.
  2. Consider neural network learning with one hidden layer containing two variables. After the network has converged, what are the parameter values? What is the Boolean function that the network represents? Are all the training examples classified correctly (if not, which aren't)? Give two examples, not in the training set, and specify what the predicted values is.
  3. For the network with a hidden layer what is a local minima of the learning rate (within one decimal point)? The value to minimize is the number of steps before the error gets below 1.0. Hint: there is a local minima in the range [0.3,7.0].

Question 2

For each question in this assignment, say how long you spent on it. Was this reasonable? What did you learn?


David Poole