home *** CD-ROM | disk | FTP | other *** search
- 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
-
-
-