Greetings
from NeuroDimension!
The World Leader in Neural Network Software
This issue of the NeuroDimension
newsletter highlights the latest developments at NeuroDimension, as well as
providing insights on how and when to use neural networks.
In this issue you’ll find:
What’s New
and News?
* Neural Network Course
Discount
Note: You are
receiving this newsletter because you requested to stay informed concerning new
developments at NeuroDimension. If you would like to stop receiving these
newsletters, please see the bottom of this newsletter for removal instructions.
=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=
The deadline is quickly approaching for a 10% early
registration discount for our next series of neural network courses. The
courses are scheduled for October 21 - October 25, 2002 at the Grosvenor
Resort, located in the Walt Disney World Resort in Orlando, Florida. Register
by September 13, 2002 to receive a 10% discount on any course!
Our course format allows both novice and advanced users to
find a suitable course. Offered courses include: "Introduction to
NeuroSolutions", "Fundamentals of Neural Networks and
NeuroSolutions", and "Advanced NeuroSolutions". The courses
include a copy of our interactive book, Neural and Adaptive Systems:
Fundamentals Through Simulations.
For details on this new offering, or to sign-up from the
Internet, see http://www.neurosolutions.com/products/course/oct_2002.html
For general ND course information, see http://www.neurosolutions.com/products/course/
For more information and samples of the interactive book,
see http://www.neurosolutions.com/products/nsbook/
=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=
NeuroSolutions Tip Box
In
previous newsletters, we discussed how you can use the Sensitivity Analysis
feature of either NeuroSolutions or NeuroSolutions for Excel to find the inputs
that do not have much effect on the network output. This allows you to remove
these inputs to produce a smaller network with better generalization (http://www.neurosolutions.com/newsletters.html
-- Volume 2 #6 and Volume 1 #4).
Sensitivity
Analysis in NeuroSolutions for Excel
In
addition to identifying the relative effect an input has on the network output,
the Sensitivity Analysis feature of NeuroSolutions for Excel gives you
additional information. It shows you how a change in each input affects the
network output. The best way to illustrate this concept is with an example.
Let’s say
that we wanted to try to create a neural network model to try to forecast the
future value of the S&P 500 stock index. As inputs we will use (1) the
interest rate on the 1-year treasure bill, (2) the average earnings per share
of the S&P 500 and (3) the average dividend per share of the S&P 500.
We will use the next day’s S&P 500 value as the desired output.
After
training a neural network using these values, we then perform the sensitivity
analysis on the Training data (from the Excel menu we select “NeuroSolutions”
then “Test Network” then “Sensitivity about the Mean”).
Viewing a
Sample Report
To view
the report produced by this experiment, open the following image in your
Internet browser:
http://www.nd.com/newsletter/images/SP500Sensitivity.jpg
Note:
Newer Internet browsers may automatically shrink large images to fit in your
browser window. If the image appears too small to read, you will want to expand
the image to regular size. In Internet Explorer, you can do this by positioning
the mouse over the image. After a moment, an icon will appear in the lower
right-hand corner of the image with four blue arrows. Click on this icon to
expand to the image to regular size.
The top
portion of this report shows the relative importance of each of the three
inputs. The lower portion graphs the input-output relationship for each of the
three inputs. The first graph shows that as the interest rates go up, the
S&P 500 goes down. The second graph shows that as the earnings per share
rises, the S&P 500 also rises. The last graph indicates that a rise in the
dividend per share corresponds to a rise in the S&P 500 index. Those that
are familiar with the stock market will find that these are expected
relationships.
For your
own application, you may not know the input-output relationships of your data
and you may be able to utilize this feature of NeuroSolutions for Excel to take
advantage of this information to better solve your problem.
Note that
this example was chosen for illustrative purposes. If you are interested in
using neural networks for the financial markets, you should also visit www.tradingsolutions.com for more
information about TradingSolutions, our neural network trading software.
=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=
We appreciate your feedback! Please send us your comments or
suggestions concerning this newsletter, our web site, or part of the
NeuroDimension product line. Write to us at: feedback@nd.com
Have questions about NeuroDimension products or training
services? Send your questions to: info@nd.com
Some mail readers may display an attachment at the bottom of
this newsletter. This is typically caused when the mail reader is set to
display text only. The original, formatted version is sometimes included as an
attachment.
This issue and previous issues of this newsletter are
available on the NeuroDimension web site at: http://www.neurosolutions.com/newsletters.html
If you would prefer not to receive these newsletters or
subsequent product updates from NeuroDimension, please reply to this letter
with the subject heading changed to the word REMOVE.
Thank you again for your support of NeuroDimension products!
