IŽve found the following pages with online courses on neural
networks. Here are the courses that are available for free. There are
several sources where the courses are only available to registerd
users and/or for fees.
Artificial Neural Networks Technology
“ This report is intended to help the reader understand what
Artificial Neural Networks are, how to use them, and where they are
currently being used.
Artificial Neural Networks are being touted as the wave of the future
in computing. They are indeed self learning mechanisms which don't
require the traditional skills of a programmer. But unfortunately,
misconceptions have arisen. Writers have hyped that these
neuroninspired processors can do almost anything. These exaggerations
have created disappointments for some potential users who have tried,
and failed, to solve their problems with neural networks. These
application builders have often come to the conclusion that neural
nets are complicated and confusing. Unfortunately, that confusion has
come from the industry itself. An avalanche of articles have appeared
touting a large assortment of different neural networks, all with
unique claims and specific examples. Currently, only a few of these
neuronbased structures, paradigms actually, are being used
commercially. One particular structure, the feedforward,
backpropagation network, is by far and away the most popular. Most of
the other neural network structures represent models for "thinking"
that are still being evolved in the laboratories. Yet, all of these
networks are simply tools and as such the only real demand they make
is that they require the network architect to learn how to use them”
(available as PDF Version[375k]  Postscript Version[2.8MB]  Text
Version[193k])
from: Artificial Neural Networks Technology
( http://psychology.about.com/gi/dynamic/offsite.htm?site=http%3A%2F%2Fwww.dacs.dtic.mil%2Ftechs%2Fneural%2Fneural_ToC.html
)
“ Neural fuzzy systems are artificial neural networks with fuzzy
input/output information. The course consists of three parts: The
first part surveys the most often used methods of approximate
reasoning and fuzzy rulebased systems. The second part covers
learning algorithms of feedforward supervised multilayer neural
networks and Kohonen's algorithm for unsupervised learning. The third
part includes learning algorithms of neurofuzzy networks. A large
number of applications of neurofuzzy systems to diagnostics, control
and decision support will be presented”
from:
( http://www.abo.fi/~rfuller/nfs.html )
An index of freeware or shareware tools for neural networks that may
be useful for you:
Neural Networks
( http://www.emsl.pnl.gov:2080/proj/neuron/neural/systems/shareware.html
)
An interstring application of neural networks:
“ A very simple neural network was developed to predict the number of
runs scored by a baseball team in a game based on total team offensive
statistics. The resulting model could then be used to:
 Compare the contribution of players to team run production
based on individual statistics.
 Determine the key statistics and their relative importance in
run production.
 Better identify the worth of individual players to the team
for the purpose of supporting salary arbitration arguments. “
from:
( http://www.zsolutions.com/an.htm )
Maybe youŽd like to read more about neural networks or meet this
association:
“ The International (INNS), European (ENNS), and Japanese (JNNS)
Neural Network Societies are associations of scientists, engineers,
students, and others seeking to learn about and advance our
understanding of the modeling of behavioral and brain processes, and
the application of neural modeling concepts to technological problems.
“
from:
( http://www.inns.org/ )
Saint Louis University offers a course “ Artificial Neural Networks
What are they? How do they work?
In what areas are they used?”
“ This report is intended to review and help the reader understand
what Artificial Neural Networks are, how they work, and where they are
currently being used. This project is a result of an assignment in AI.
The report is a nontechnical report, thereby it does not go into
depth with mathematical formulas, but tries to give a more general
understanding”
from:
Artificial Neural Networks
( http://hem.hj.se/~de96klda/NeuralNetworks.htm )
Search Stategy:
I visited yahoo.com in the category:
( http://dir.yahoo.com/Science/Engineering/Electrical_Engineering/Neural_Networks/
)
and
( ://www.google.de/search?sourceid=navclient&hl=de&querytime=aAg&q=%22Neural+Networks%22+%22online+course%22+
)
If this answer does not meet your needs, please request clarification
and I'll be happy to look into this further.
tillga 
Clarification of Answer by
tillga
on
26 Jul 2002 10:50 PDT
Hello,
Sorry that my first answer didnŽt fully satisfy. Was (
http://hem.hj.se/~de96klda/NeuralNetworks.htm ) not what youŽre loking
for ?
Here are some more examples:
"Artificial Neural Networks
An introductory course by Anthony Zaknich
This book can be used as a textbook for an undergraduate or
postgraduate introductory course on ``Artificial Neural Networks for
Pattern Recognition, Signal Processing and Control''. The course
material covers the fundamentals of Artificial Neural Networks (ANN)
from both theoretical and practical application perspectives. The aim
is to present a design approach, enough tools and sufficient
understanding of ANNs to be able to apply them to typical problems in
pattern recognition, signal processing and controls. Its content can
be adequately covered in twenty six standard forty five minute
lectures.
"
from:
Artificial Neural Networks
( http://www.maths.uwa.edu.au/~rkealley/ann_all/ )
"Neural networks have seen an explosion of interest over the last few
years, and are being successfully applied across an extraordinary
range of problem domains, in areas as diverse as finance, medicine,
engineering, geology and physics. Indeed, anywhere that there are
problems of prediction, classification or control, neural networks are
being introduced. This sweeping success can be attributed to a few key
factors:
Power. Neural networks are very sophisticated modeling techniques
capable of modeling extremely complex functions. In particular, neural
networks are nonlinear (a term which is discussed in more detail later
in this section). For many years linear modeling has been the commonly
used technique in most modeling domains since linear models have
wellknown optimization strategies. Where the linear approximation was
not valid (which was frequently the case) the models suffered
accordingly. Neural networks also keep in check the curse of
dimensionality problem that bedevils attempts to model nonlinear
functions with large numbers of variables.
Ease of use. Neural networks learn by example. The neural network user
gathers representative data, and then invokes training algorithms to
automatically learn the structure of the data. Although the user does
need to have some heuristic knowledge of how to select and prepare
data, how to select an appropriate neural network, and how to
interpret the results, the level of user knowledge needed to
successfully apply neural networks is much lower than would be the
case using (for example) some more traditional nonlinear statistical
methods."
from:
Neural Networks
( http://www.statsoftinc.com/textbook/stneunet.html )
Hope these will help now.
tillga
