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: CVDave who wrote (220)	10/9/1998 8:20:00 PM
From: CatLady	Read Replies (2) \| Respond to of 805

CVD - " Maybe it doesn't matter, as long as the net predicts properly, like your COMS net, eh? Well, I'd sure like to know what I did right so that I can do it again! Your explanation of neurons and weights was helpful. I'm leaning towards always using the maximum amount of historical data that NS will allow and that is available. That would be an argument for upgrading from the shareware (1000 days) to commercial (2000 days). But there is the issue of how the trading patterns of a stock can change over time. One thought I have on that is that one is more likely to find a consistent pattern among the more liquid large cap stocks than in the small caps. Any other thoughts on that issue anyone? I also wonder how Simulated Annealing fits into the picture. Has anyone done any experiments with nets only trained on BackProp or only on Annealing? CL