INTRODUCTION
------------
Thanks for trying the shareware version of QwikNet.  QwikNet is a 
powerful, yet easy to use artificial neural network simulator.  
QwikNet implements several different algorithms to train a standard 
feed-forward neural network in an easy-to-use graphical 
environment.  The shareware version is limited to a maximum 
of 1 hidden layer and 10 hidden neurons.  The registered version can 
accommodate up to 5 hidden layers with no limits (besides hardware) 
on the number of hidden neurons.  

You may evaluate this software free for 30 days, after which you must 
either purchase the registered version or delete the software from
your machine.

Please feel free to distribute the file QwikNet.ZIP to friends, associates,  
or to a computer bulletin board system (BBS).

REGISTRATION
------------
The registration fee is $40 US.  Please print and fill out the 
registration form in the file 'register.txt', (also found 
in the help file), and enclose it with your payment.  Upon 
receipt of payment you will receive the full registered version 
and all future upgrades.  


INSTALLATION
------------
The 32-bit version, QwkNet32.EXE, requires a minimum 486 
processor and Windows 95 or NT.  This version removes 
all practical limits on network/data file size.

Installation of both versions, including the DLLs and 
help files, requires less than 1.5 MB of disk space.


32 bit version - copy the following files to your directory:

	QwkNet32.EXE 	- 32 bit executable for Win95 or NT
	BWCC32.DLL     	- 32-bit DLL needed by QwkNet32
	QwikNet.HLP	- Windows help file
	README.TXT	- This file
	REGISTER.TXT	- A registration form in ASCII format
	FILE_ID.DIZ	- Information file for bulletin boards 
	Example data files - optional

EXAMPLE DATA FILES
------------------
Several example data files are included for testing:

SINCOS.TRN  -  	Training data file with one input (x)
		and two outputs Sin(x) and cos(x).
SINCOS.TST  -   Testing data for SINCOS.
SINCOS.WTS  -	Example of saved weights.
SINCOS.NET  - 	SINCOS project file.

SECURITY.*  -	A more complex data set for Power System Security
		analysis.  The data set contains 33 inputs 
		(power system features) and 1 output 	
		(security classification).

XOR.*       -   XOR training data set.
 		Two inputs and 1 output.


QUESTIONS/COMMENTS
------------------
Please send any questions, comments or bug reports to:

	Craig Jensen
	9935 NE 125th Ln #4
	Kirkland, WA 98034
	email - cjensen@ee.washington.edu