CS322 Fall 1999
Module 12 (Neural Network Learning)
Assignment 12
Due: 1:30pm, Friday 3 December 1999.
The following is the same data from assignment 11:
Example  bought  edu  first  visited  more_info 
e_{1}  false  true  false  false  true 
e_{2}  true  false  true  false  false 
e_{3}  false  false  true  true  true 
e_{4}  false  false  true  false  false 
e_{5}  false  false  false  true  false 
e_{6}  true  false  false  true  true 
e_{7}  true  false  false  false  true 
e_{8}  false  true  true  true  false 
e_{9}  false  true  true  false  false 
e_{10}  true  true  true  false  true 
e_{11}  true  true  false  true  true 
e_{12}  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.
 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.
 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.
 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].
For each question in this assignment, say how long you spent on it.
Was this
reasonable? What did you learn?
David Poole