Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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 : Systems, Strategies and Resources for Trading Futures -- Ignore unavailable to you. Want to Upgrade?

To: Patrick Slevin who wrote (6707)	10/19/1998 12:50:00 PM
From: jjs_ynot	Read Replies (1) \| Respond to of 44573

It appears that you will need to invest a significant amount of time and $ in building the infrastructure to support a Neural Net with no assurance that it will be successful.

To: Patrick Slevin who wrote (6707)	10/19/1998 12:58:00 PM
From: Nemer	Read Replies (1) \| Respond to of 44573

as concerning the neural net seminar ---- I hope that any discussion will fall into the on topic area as the headline for the thread specifically calls for "resources" ....... Damg ----- for an engineer, you have very well expressed, in a concise manner, my many years of working with the output data of a neural net as I'm too retarded mentally to write the formulas necessary for the handling of the input data ......... and I quote you =====> Using one requires a lot of work and a lot of tolerance for going down Dead Alleys. Unless a dedicated effort is made, I am certain one could try to build a successful model for years and never succeed. Further, even with a dedicated effort there are no guarantees and unusual market changes mean one has to constantly stay on top of the models. Amen, brother, AMEN ........ I've had numerous emails and private messages asking why I have shut down the BBx .... with my programmer out I'm out ....... As to what you've learned and what you're to learn, good luck. We found it necessary to buy the time on a mainframe due to just the time constraints of what you posted ..... and even then it consumes hours. I can remember, last year, a long drawn out email correspondence with a member of SI, who no longer posts to me, because he couldn't understand how, if he asked me to research a single parameter he felt was valuable, that it could take me a whole day to come up with a nonconclusive answer .......... ggggggggg so he quit talking and I quit writing ......... The back testing (as in the case of VIX that you brought up) is next to impossible, even with multi gigs of data storage ...... which one MUST have to do any backtesting ...... Maybe it's just as well that I've gotten old and my programmer is ill ...... heck, it tires me out just talking bout it ......... gggggg Nemer