I am very pleased to write the Foreword to this unique volume since I believe it is a very special
publication that stands out among many others. It is about neural networks as practical tools
capable of building trainable computing models. After training is completed, the models can
provide solutions to difficult problems easily by capturing and interpreting knowledge from data.
These neurocomputing models—as we call them—mimic nature and their biological prototypes
such as brain and sense in their essential learning and adaptation abilities.
These naturally inspired models derive their power from the collective processing of neurons

whose main advantage is the ability to learn and adapt to changing environments. As such tech-
niques typically return encapsulated knowledge, the old adage that “knowledge is power” can be

thus applied to all the neurocomputing models described in this book.

The study of any subject including neural networks can be made much easier and more pleas-
ant if we acquire hands-on experience and simulate and visualize our experiments on a PC instead

of reading theories. This book offers a real-life experimentation environment to readers. Moreover,
it permits direct and personal exploration of neural learning and modeling.
The companion software to this book is a collection of online programs that facilitate such
exploratory methods and systematic self-discovery of neural networks. The programs are available
in two forms—as executable applications ready for immediate use as described in the book or
as source codes in C#. The source code format allows users’ modifications. Its parts can also be

embedded into users’ programs designed for various educational, research, or practical data analy-
sis tasks. All programs are fully functional and their codes are usable for object-oriented design.

This feature makes them easy to use without going into the details of the algorithms used.
The planned experiments are interesting and attractive, and running them can be regarded as
playing a computer game. However, the unique insights of computational learning gained this way
are both entertaining and educational at the same time. Guided self-activity has again trumped
the passive study of theorems and axioms.
The book is written in a very convincing narrative, and can be easily followed by people outside
the science–technology–engineering–mathematics (STEM) areas. To take advantage of neural

networks as tools, such readers need only introductory experience in handling and editing com-
puter files—knowledge that most of us have. In addition, the book can be read by high school

students and hobbyists who have no formal computer training. Readers may be surprised, but
throughout the book they will not find even a single mathematical formula! At the same time
the source codes allow interested persons to become familiar with fine details of simulations and
algorithms. Such details can be simply reverse-engineered from the codes of the program.