NeuroStock Message Board

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 : NeuroStock

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Bill Scoggin who wrote (506)	12/27/1998 4:30:00 PM
From: Bob Anderton	Read Replies (2) of 805

Thanks Bill, In your estimation, going from NS20S to either NS40S for $70 or NS20 for $200, which gives you the most bang for the buck? the extra 20 neurons or the commercial version vs the shareware? In other words, how useful is the added fuctionality of the commercial version relative to more neurons. Thanks in advance for addressing a vague question. Another question: The trading results indicate how the model did relative to a buy and hold approach over the entire training and verification set, but you would expect good performance during the data the model is trained on. Is there a way to compare the performance just during the verification period? Am I correct in thinking that this is the important metric? Or do people really only consider how the model does after the verification period by paper trading the model for a while? I've noticed that one drag of this approach vs regular TA indicator building and system testing is that any change you want to make to a NN requires retraining (hours!) as opposed to the instant feedback you get with regular systems based on indicators. Hope everyone had a great Christmas. Bob

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next