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 (541)	12/31/1998 11:37:00 AM
From: Bill Scoggin	Respond to of 805

Jay, For a given input set of numbers, at least with backpropagation,the ones of them that DO have a bearing on the calculated output of the network will be recognized and their associated weight values will be increased for the next training iteration. The ones that DON'T have much affect on the output will have their weight values changed toward zero, and eventually will basically be ignored by the network. I would guess that whether or not you chose price, l/t filter, etc., the network will evaluate its usefulness during training - so, it probably doesn't matter! At the expense of slower training, why not try Both to see what happens? It will be interesting to see what the differences in the nets would be after a day or two of training. Just a thought... Bill