Short:        Neuronal network library (C++)
Architecture: m68k-amigaos

     This package contains all the functions necessary to generate a
Neural network which you can train and use in your programs.  The
Neural network has an input layer, two hidden layers, and an ouput layer.
The network is feedforward and fully connected.  You may specify an size for
each layer at run-time.  This code is Public Domain and anyone can use it in
any type of program.

     There are two versions of the Neural network code, the C version and
the C++ version.  First the code was written in C, then it was written in C++
making it a class.  Finally it was written back in C keeping the class-like
structure.  For the C programmers who are not familiar with C++ constructs,
you should read the file C_programmers.readme

The following files are included in this package:
C++ files
Neural_network.cc --> C++ Neural_network class code
Neural_network.h  --> C++ Neural_network header file
xor_dbd.cc        --> Example of how to solve the XOR problem using the
                      delta bar delta rule.
xor_bp.cc         --> Example of how to solve the XOR problem using
                      straight back propagation.
weights.xor       --> Initialized weights that are read in by the XOR programs
                      because the gcc,gpp rand () function generates a new
                      sequence of random numbers everytime the program is
                      run.  This file makes sure every XOR training session
                      starts at the exact same place so you can see how
                      changing learning parameters affects the rate of
                      convergence.

C files
Neural_net.c --> C Neural network 'class' code
Neural_net.h --> C header file for 'class' and functions
xor_c_dbd.c  --> Example of how to solve the XOR problem using
                 the delta bar delta rule.
xor_c_bp.c   --> Example of how to solve the XOR problem using
                 straight back propagation.
weights.xor  --> Same file as above for the same reason.


Document files
Readme.1st           --> This file
Neural_network.doc   --> Explanation of each Neural network function.
C_programmers.readme --> Basic explanation of how C++ works so C
                         programmers can understand Neural_network.doc

I will most likely not be supporting the C code after this version because
I much prefer to program in C++.  However, if there are bugs in either
version, please let me know and I will fix it as soon as I can.  You can
email me at

anstey@sun.soe.clarkson.edu