home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
HPAVC
/
HPAVC CD-ROM.iso
/
NEUCLS3.ZIP
/
NURN.ZP
/
POLC.HLP
< prev
next >
Wrap
Text File
|
1994-08-19
|
3KB
|
85 lines
Functional Link Training and Testing Program
Outline
1. Program Purpose;
2. Network Characteristics;
3. Files Needed or Produced;
4. Example Run of Functional Link Program
5. Error Functions
1. Program Purpose;
a. Initialize a functional link network
b. Train the network using a fast training method
c. Process data files using the network
2. Network Characteristics;
a. Activation Functions; Sigmoidal ( Out = 1/(1 + exp(-Net)) ) output
units
b. Net Functions; polynomial functions of the inputs, with
user-chosen degrees of 1 to 5.
3. Files Needed or Produced;
a. The network structure file; stores the number of inputs and outputs,
and the polynomial degree.
b. The training or testing data file, which gives example inputs
and outputs for network learning, or for testing after learning.
Al data files are in formatted, IANS form, which means that
each pattern or feature vector is followed by the correct class
number.
c. The non-demo version saves weights.
4. Example Run of Functional Link Program
a. Go to the "Batch Processing" option and press <ret>
b. Observe the parameter file with commented keyboard responses;
5 ! # of training iterations
2 ! 1 for old net structure file, 2 for new one
2 16 ! degree and number of inputs
4 ! # of outputs (one per class)
Grng.tp ! network structure filename
2 ! outputs not coded (1 per class)
Grng ! data filename
0 ! # of patterns to read (0 to read all training data)
1 ! examine some data
1 2 ! examine patterns 1 and 2 (training begins here)
4 ! stop
The program will read all patterns from the file grng, and train a
functional link net using the network structure file grng.tp, which
is shown below.
2 16 4
153 4
The network will be 2rd degree with 16 inputs and 4 outputs
(one for each of the four classes). The final network weights
will not be saved in the demo version.
c. Exit the DOS editor and observe the program running
d. Go to the "Examine Program Output" option and press <ret>
e. You can run this program on your own data, simply by editing the
parameter file in the "batch Run" option.
5. Error Functions
a. The error function that is being minimized during functional link
training is
Npat Nout 2
MSE = (1/Npat) SUM SUM [ Tpk - Opk ]
p=1 k=1
where Npat is the number of training patterns, Nout is the number
of network output nodes, Tpk is the desired output for the pth
training pattern and the kth output, and Opk is the actual output
for the pth training pattern and the kth output. The desired
output Tpk is 0 for the correct class and 1 for other classes.
MSE is printed for each iteration.
b. The error percentage that is printed out during training is
Err = 100 x (number of patterns misclassified/Npat).