a set of C++ library classes
for neural networks development



Output of nn application.

Output format of the application for training and testing Multi Layer Perceptrons (MLP) and single layer perceptrons.
The application print on standard output the following informations:

See also nn

Example:
This example shows the output of a Standard MLP for a 7 classes classification problem:

 
Standard Multi-Layer-Perceptron
Number of layers: 2
Input dimension: 4
Number of hidden units: 7
Number of classes: 7
Output dimension: 7
Minimum Hamming distance between class codewords: 2
Stop conditions:
Maximum number of iterations : 2000
Threshold normalized RMS error : 0.05
Learning algorithm: Alg. Gradient descent
Learning rate : 0.3
By pattern learning.
Training results:
RMS normalized error = 0.0536067
Iterations = 2000

Testing :
Neural network stored in mynet.net
Neural network output stored in mynet.out
Confusion matrix :
    6     0     0     0     0     0     0 
    0     9     0     0     0     0     0 
    2     0     9     0     0     0     0 
    0     0     0     7     0     0     0 
    0     0     0     2     9     0     0 
    0     0     0     0     0     9     1 
    0     0     0     0     0     0     8 

Neural net errors:
Number of errors  :  5  :  Percentual error rate  :  8.06452 %
CPU time (min.sec) : 0.31 : 

Alphabetic index Hierarchy of classes


Last Updated February 2001
For comments and suggestions mail to Giorgio Valentini