Re: Proof that neural nets work


John Moody <john.atwell.moody@xxxxxxxxx> wrote in message
news:1148023936.895514.218220@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Two important announcments.

I'll alert the media...

1. The text file
http://www.goldengem.co.uk/proof.txt contains complicated combinations
of trig functions. Also the website has the a free neural net (same
site, omit /proof.txt). Point it at the data and you can really see how
well it predicts these complicated functions. This shows, if there is a
pattern, a neural net will see it.

Since you are posting this on a stock newsgroup, are you implying
that stock prices can be predicted by linear, albeit "complicated"
trig functions? If we could devine what these functions are, similar
to "attractor reconstruction" in chaos theory, could we then just throw
the nueral net away and use the functions to predict the market?

2. On 17 May the configuration of GoldenGem was enlarged, not a lot,
but it has made a tremendous difference. The photos are proof of that,
and you can try it yourself.

You took a picture of a neural net?

If you have a reg number or are during
trial interval, you are welcome to download the improved version.

How is it different from other freely-available neural net software,
other than being visually (?) bigger?

---
William Ernest Reid
Post count: 360



.