=============================================================================
	README file for the example files dlvq_ziff.xxx
=============================================================================


Description:	This network is a toy digit recognition network.
============	

This network is demonstration of the dlvq learning algorithm.
The untrained network (dlvq_ziff.net) has an 16x16 input layer and 1 output unit.
The trained network (dlvq_ziff_trained.net) has an 16x16 input layer, an 10x1  hidden layer and 1 output unit.

Pattern-Files:	dlvq_ziff_100.pat
==============	

The pattern-file dlvq_ziff_100.pat contains 100 training patterns (a random
number of each digit)

Network-Files:	dlvq_ziff.net
==============	dlvq_ziff_trained.net

Config-Files:	dlvq_ziff.cfg
=============	
 
Topology: 256 Input-Neurons
          (10) Hidden-Neurons (only for the trained net)
          1 Output-Neuron


Hints:
======

The following table shows the learning functions one can use to train
the network. In addition, it shows the learning parameters and the
number of cycles needed to train the network successfully.

These parameters have not been obtained with extensive studies of
statistical significance. They are given as hints to start your own
training sessions, but should not be cited as optimal or used in
comparisons of learning procedures or network simulators.


Learning-Function               Learning-Parameters       Cycles

Dynamic_LVQ            		0.03 0.03 10              1


Dynamic_LVQ needs for training exactly one Output-Unit.
The Init-Funktion must be DLVQ_Weights.
=============================================================================
	End of README file
=============================================================================