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: INFO_DART who wrote (256)	10/17/1998 10:17:00 AM
From: CatLady	Read Replies (1) of 805

Are you familiar with NeuroStock? The large number of variables available in designing a network, and the length of time it takes to train a network make developing an experiment that would satisfy an academic research project in a reasonable amount of time an unreachable goal. NS is most likely not the best product to use if you want to do scientifically rigorous research, due to is 'black box' aspects. I also believe there are other NN tools available which give more feedback on how much individual inputs contribute to a net. I've experimented with NN design variations on a single stock. But I've been frustrated because what I learn through those experiments does not generalize well to other stocks. My goal is not PhD quality research, it's building Nnets which are profitable in real-world trading results. I'm interested in learning all I can in order to reach that goal.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next