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 : NeuroStock -- Ignore unavailable to you. Want to Upgrade?

To: Jay Hartzok who wrote (487)	12/17/1998 11:16:00 PM
From: Jay Hartzok	Respond to of 805

I'D LIKE TO TAKE THIS OPPORTUNITY TO WISH EVERYONE ON THE THREAD A VERY HAPPY AND JOYOUS HOLIDAY SEASON, AND MAY 1999 BE A PROFITABLE YEAR FOR ALL OF US. Jay

To: Jay Hartzok who wrote (487)	12/17/1998 11:34:00 PM
From: Vic Nyman	Read Replies (1) \| Respond to of 805

Jay & CatLady, Thanks for the help. ( I hope I am doing something stupid. ) I have upgraded to the commercial version. For the sake of this testing, I have limited the nets to a fixed 20 neurons. I am using the Up/Down option in the training. The trades in the training window are very close, but not exact. Most are the same, but a few dates are a little different and in 1 instance there is an extra trade. I attribute this to the low number of training cycles ( I ran the nets in BackProp until they stabilized ... at 2000 cycles for both. ) I am running longer, overnight tests now, but the results are not changing. I would characterize the differences described above as being very small. Nothing like the differences I am seeing in the verification window. After this round is finished... I will try another stock to see if I can duplicate the problem in another net. Vic