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 |
