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: CatLady who wrote (265)	10/18/1998 8:45:00 PM
From: Len Giammetta	Read Replies (1) \| Respond to of 805

CatLady, thanks for the point. There's some interesting stuff there.

To: CatLady who wrote (265)	10/19/1998 1:09:00 AM
From: Jay Hartzok	Read Replies (3) \| Respond to of 805

CatLady, I did some experimenting with training nets, using only simulated annealing training, no back propagation. Results from this have been somewhat disappointing to say the least. It appears to me that the training process of simulated annealing needs some sort of a coherent base net {a net pretrained with back propagation} to start its training process from. If it doesn't have this foundation to start with, the annealing process seems to get "confused". I have e-mailed Andrew asking for his input on this subject and am waiting for his response. If conditions in San Antonio are as bad as the news leads you to believe, it might be awhile until he responds. Jay