=================================================================================
      BREAST CANCER DIAGNOSIS SAMPLE
      Copyright 2004 Pejman Makhfi				Date: Feb. 23, 2004
=================================================================================
DISCLAIMER: THIS WORK IS PROVIDED "AS IS." THE COPYRIGHT HOLDER AND THE          
CONTRIBUTING AUTHORS OF THIS WORK MAKE NO REPRESENTATIONS OR WARRANTIES (i)      
EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, 
FITNESS FOR A PARTICULAR PURPOSE, TITLE OR NON-INFRINGEMENT; (ii) THAT THE       
CONTENTS OF SUCH WORK ARE FREE FROM ERROR OR SUITABLE FOR ANY PURPOSE; NOR THAT  
IMPLEMENTATION OF SUCH CONTENTS WILL NOT INFRINGE ANY THIRD PARTY PATENTS,       
COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS. IN NO EVENT WILL THE COPYRIGHT HOLDER    
AND THE CONTRIBUTORS TO THIS WORK BE LIABLE TO ANY PARTY FOR ANY DIRECT,         
INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES FOR ANY USE OF THIS WORK, INCLUDING,  
WITHOUT LIMITATION, ANY LOST PROFITS, BUSINESS INTERRUPTION, LOSS OF PROGRAMS OR 
OTHER DATA ON YOUR INFORMATION HANDLING SYSTEM OR OTHERWISE, EVEN IF THE         
COPYRIGHT HOLDER OR ANY CONTRIBUTORS TO THIS WORK IS EXPRESSLY ADVISED OF THE    
POSSIBILITY OF SUCH DAMAGES.                                                     

Permission to use and distribute of this file and its accompanying documentation
for any purpose and without fee is hereby granted in perpetuity, provided that   
the above copyright notice and this paragraph appear in all copies.              
=================================================================================

BREAST CANCER DIAGNOSIS SAMPLE

This neural network is trained to recognize symptoms of breast cancer.
It was trained with cancer dataset from UCI machine learning database
(ftp://ftp.ira.uka.de/pub/neuron/proben1.tar.gz)
As for NN architecture, this is a 2-layer perceptron with 6 logsig neurons on the 
hidden layer and single logsig output neuron.
There are 9 inputs attributes, all discrete on a scale 1 - 10
(1=lowest; 10=highest):

NNDef auto-scale function is used for normalization:

   1. Clump Thickness               1 - 10
   2. Uniformity of Cell Size       1 - 10
   3. Uniformity of Cell Shape      1 - 10
   4. Marginal Adhesion             1 - 10
   5. Single Epithelial Cell Size   1 - 10
   6. Bare Nuclei                   1 - 10
   7. Bland Chromatin               1 - 10
   8. Normal Nucleoli               1 - 10
   9. Mitoses                       1 - 10

There's a single output, which varies from 0 for benign and 1 for malignant.

