[EMAIL PROTECTED] wrote:
[snip]
On the bug-tracker there's a patch proposed by Michel Delpreli : Jon
said it didn't solve the problem, but if you understand the intended
modification maybe you can get a clue at what's happening ...
I've just retried the patch and it still fails for me, here's
On Wed 23 Aug 2006 (13:58 +0100), Jonathan Kinsey wrote:
[EMAIL PROTECTED] wrote:
[snip]
On the bug-tracker there's a patch proposed by Michel Delpreli : Jon
said it didn't solve the problem, but if you understand the intended
modification maybe you can get a clue at what's happening ...
Sounds like a more educated fix, however, it doesn't quite work:
You have already rolled the dice.
1. Cubeful 0-ply2/af 1/afEq.: +0,722
0,861 0,000 0,000 - 0,139 0,000 0,000
0-ply cubeful prune [ekspert]
2. Cubeful 0-ply2/1 2/af
On Wed 23 Aug 2006 (17:39 +0200), Christian Anthon wrote:
Sounds like a more educated fix, however, it doesn't quite work:
Nope, I'm working on it. I did a quick hack on a test system (not
current) and, as luck would have it, it looked normal, but there is
more setup to be done. I should have it
I've been trying to get information on this, by looking up the archives, but
with limited luck, so I'll just ask the experts:
1) Can a user do their own neural net training without necessarily being a
full-fledged programmer? I'm presuming/hoping they can.
2) Presuming it is possible, what are
Albert Silver wrote:
I've been trying to get information on this, by looking up the archives, but
with limited luck, so I'll just ask the experts:
1) Can a user do their own neural net training without necessarily being a
full-fledged programmer? I'm presuming/hoping they can.
The simple
On Wed 23 Aug 2006 (17:44 +0200), Jim Segrave wrote:
On Wed 23 Aug 2006 (17:39 +0200), Christian Anthon wrote:
Sounds like a more educated fix, however, it doesn't quite work:
Nope, I'm working on it. I did a quick hack on a test system (not
current) and, as luck would have it, it looked
Ok, so if I understand it, I can access and use some training, but cannot
change the fundamental aspects such as the inputs, or the nets (as in adding
new ones).
You see, while scouring the archives, I saw from a discussion from not long
ago, that Ian Shaw had managed to get the plain TD
On Wed 23 Aug 2006 (20:29 +0200), Jim Segrave wrote:
On Wed 23 Aug 2006 (17:44 +0200), Jim Segrave wrote:
On Wed 23 Aug 2006 (17:39 +0200), Christian Anthon wrote:
Sounds like a more educated fix, however, it doesn't quite work:
Nope, I'm working on it. I did a quick hack on a test
