[Points: 10; Issued: 2003/03/14; Deadline: 2003/04/04; Tutor:
Martin Ebner; Infohour: 2003/04/02, 14:00-15:00,
Seminarraum IGI; Einsichtnahme: 2003/05/14, 14:00-15:00,
Seminarraum IGI; Download: pdf; ps.gz]
This homework assignment asks you to apply backprop to a
regression problem: the Boston Housing data set. The file housing.zip contains the data as the file
housing.mat. See the file
housing-description.txt which is also contained in
housing.zip for more information on the data set.
- Initialize the random number generator using the Matlab
- Split the data randomly into a training set (2/3) and a test set (1/3) (use the function
- Normalize the data such that each attribute has a zero mean and
a variance of 1 (use the function
- Train a 2 layer feed forward network with 2 hidden units and
one output unit on the training set (use proper activation functions at each layer)
net.trainParam.epochs=150 epochs and the training
standard parameters. Describe how the error on the training and on
the test set changes with the number of epochs.
- Investigate how the error on the test set changes if one uses
only the first 10%, 20%, 50%, or 75% of the set for training (same network as in
3). In particular create a plot which shows how the error on the
test set after 150 epochs depends on the size (10%, ..., 100%) of
the training set. Interpret the resulting plot.
- Repeat step 5) but with a network with 20 hidden units.
- Compare the results obtained in 5) and 6).
- Present your results clearly,
structured and legible. Document them in such a way that anybody
can reproduce them effortless.
- Please hand in the print out of the
Matlab program you have used.
- trainbfg is an enhanced
gradient descent method which usually converges faster than the
default backprop algorithm.