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: Vic Nyman who wrote (383)	11/14/1998 5:10:00 PM
From: Jay Hartzok	Read Replies (1) \| Respond to of 805

Vic, I see you just joined SI. Welcome to the thread and don't be a stranger. Are you running the commercial version or shareware, and how many neurons? Jay

To: Vic Nyman who wrote (383)	11/15/1998 10:56:00 AM
From: CatLady	Read Replies (1) \| Respond to of 805

Vic, Interesting comments on annealing. Based on Jay's and your posts, I've continued to test annealing and am still getting mostly poor results. I see from a later post that you're running a PII, which is significantly faster than what I'm running, which is a Cyrix 200. I wonder if I'm just not allowing annealing enough compute cycles to do its' thing adequately. I think I've read that the Cyrix chip FPU is slower than an Intel FPU, if so, I may order a Intel 233MMX CPU, which is as fast as this motherboard will support. How long do you allow annealing to run? Do you keep both Backprop and annealing checked and allow NS to decide which to run? If anything, it seems that annealing might help an already good net, but it won't turn a marginal net into a good one. To All - Comments on any of this? P.S. - The illegal operation error I get is quite infrequent and just slightly annoying, not destructive.