readme

人智算法基本程序

					    PDP Program


Welcome to the wonderful world of the PDP C++ directory. This program
demonstrates training a neural network. It is meant to be a companion
to chapter 5 of the "Artificial Intelligence" textbook.  This code was
written by Jon Monsarrat, [e-mail].

Five sections describe the program:

1. The problem
2. Building the program
3. Running the program
4. The solution, and how to read the source code

----------------------------------------------------------------------
1. The problem

The book goes into quite some detail about the problem, but here it is
in a nutshell.

We have a neural net and a function to train it on. Now we need to 
figure out how to adjust the weights so that the function is learned.

----------------------------------------------------------------------
2. Building the program

The source code in this directory is complete and does not depend upon
any other source code from the textbook. It only uses standard
and libraries which should come any C++ compiler.

You can build this program in UNIX by simply typing

      make

You may need to edit the Makefile to change the name of the compiler,
if you do not have a compiler named "CC".

To add a function, you will need to recompile the program. You'll also
need to recompile the program to supply your own neural net.

----------------------------------------------------------------------
3. Running the program

Running the program is very simple. Just type

   pdp1 [-or] [-and] [-xor] num_attempts learning_rate
        -or  use the 2 bit or  algorithm
        -and use the 2 bit and algorithm
        -xor use the 2 bit xor algorithm
        num_attempts is the number of training attempts
        learning_rate is the learning rate, try 1 or 2

The program pdp2 works similarly, but for a different neural net.
----------------------------------------------------------------------
5. The solution, and how to read the source code

This program is quite similar to the Lisp program. The neural net
code is stored in PDP1.C and PDP2.C. The training code is in PDP.C.

There is one wrapper class, PDP, but it does not really do much.
Effectively, this program is just a C program.
----------------------------------------------------------------------