SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Strategies & Market Trends : Neural Nets - A tool for the 90's -- Ignore unavailable to you. Want to Upgrade?


To: Optim who wrote (22)12/29/1997 8:37:00 PM
From: current trend  Read Replies (1) | Respond to of 871
 
Since input selection,management, and massage
are so critical to the ultimate neural net output
---would you speak to your experiences and offer advice
as to how to best aproach this task?

Over optimization is the first deadly sin of TA...
not so with NN?

Are the nets finding non linear relationships
that we can not see or just using computational
power to discover subtilities about the edges
that produce their effectiveness?

CT



To: Optim who wrote (22)12/30/1997 2:21:00 AM
From: current trend  Read Replies (1) | Respond to of 871
 
In reading your posts it appears you have experience
with several different NN software packages. Besides
price how do they differ? Since you are presently
using neuroshell, is it the best? I've noticed that neurostock
offered varying numbers of "neurons" along differing
price points. As to ease of use my background is
non engineering with limited computer experience
other than running common off the shelf software
packages. Does one need extensive computer
language writing abilities?

Can you speak to the amount of time it takes to
get a NN up and running with the type of results
upon which you would risk your hard earned dollars?
I presently use a system of about 25 price based
indicators to make buy/sell decisions. Is this too many
to feed into a NN?

Thanks in advance--

CT



To: Optim who wrote (22)12/31/1997 8:20:00 PM
From: J. Salbans  Read Replies (1) | Respond to of 871
 
Thanks for the informative post. One quality I am interested in is the potential for having a system which could give not only buy and sell signals, but could also estimate error boundries such that one could have information on the estimated "range" of profit at a given point. This seems to me to be the type of problem which is well suited to a fuzzy logic methodology (possibly GA). Is anyone aware of products which combine fuzzy logic/GA/neural nets to address problems such as this?

thanks--out for '97.
happy new year to all.