Search the web
Sign In
New User? Sign Up
easynn · Neural Planner Software Ltd
? Already a member? Sign in to Yahoo!

Yahoo! Groups Tips

Did you know...
Want to share photos of your group with the world? Add a group photo to Flickr.

Best of Y! Groups

   Check them out and nominate your group.
Having problems with message search? Fill out this form to ensure your group is one of the first to be migrated to the new message search system.

Messages

  Messages Help
Advanced
Messages 817 - 846 of 1554   Oldest  |  < Older  |  Newer >  |  Newest
Messages: Simplify | Expand   (Group by Topic) Author Sort by Date ^
817
Hello Steve Just like walt <WSCHWARZ@> I am surprised by your move. I usually program with PB-CC and WIN ( I am not saying here to use PB) but what the other...
j88cj
Offline Send Email
Jan 2, 2006
3:45 am
818
Hello Guy, ... I'm not using DOT NET. The reason I am switching to VS2005 is to move my code to VC++ 8. Getting rid of the old non standard functions is not as...
steve@...
easynn
Offline Send Email
Jan 2, 2006
10:14 am
819
Hi , I am somewhat novice to using neural networks ... My question is , what is the criteria one is looking for when training a net ? I have heard of...
alex
kryer_99
Offline Send Email
Jan 4, 2006
4:17 am
820
Hello Alex, ... Use some of the example rows for validating. Stop training when the best validating results are found. ... EasyNN-plus will usually find the...
steve@...
easynn
Offline Send Email
Jan 4, 2006
11:29 am
821
OK , thanks Steve . I guess you are saying there is nothing too mysterious about it . Good enough for me . Thanks again . ... From: steve@... To:...
alex
kryer_99
Offline Send Email
Jan 5, 2006
3:14 am
822
The first beta release of EasyNN-plus 7.0h is now available for testing. This is a full rebuild after moving from VC++ 6 to VC++ 8. Many source code changes...
steve@...
easynn
Offline Send Email
Jan 13, 2006
11:43 pm
823
Just in case you did not spot my error with the subject name, I put 7.0a by mistake. Here is the message again. The first beta release of EasyNN-plus 7.0h is...
steve@...
easynn
Offline Send Email
Jan 15, 2006
3:01 pm
824
Version 7.0h is now available. The problems found in the beta copy have been fixed. The changes are:- 1. Replaced deprecated code with C++ standard, supported...
steve@...
easynn
Offline Send Email
Jan 19, 2006
2:07 pm
825
I have an error message that pops up that says ... "Grid contains validating data outside the training range . Use Action > Check Grid to locate the problems...
alex
kryer_99
Offline Send Email
Jan 21, 2006
5:55 am
826
Hi Alex, ... It means that some of your validating examples are outside the range of the training examples. Validating data must be within the training range....
steve@...
easynn
Offline Send Email
Jan 21, 2006
10:37 am
827
Hi Steve , That kind of makes it hard to create a validation set then . I have 3000 patterns and I have to choose now about 300 validation patterns that are...
alex
kryer_99
Offline Send Email
Jan 21, 2006
8:21 pm
828
Hi Steve , Well , I just used random validation patterns .. Problem now is that after learning is done , the ouput it gives me to my query inputs is not...
alex
kryer_99
Offline Send Email
Jan 21, 2006
9:16 pm
829
... What were the validating results? How did you decide that learning was done? -- Steve Wolstenholme Neural Planner Software EasyNN-plus. The easy way to...
steve@...
easynn
Offline Send Email
Jan 21, 2006
10:17 pm
830
Hi Steve , I am not sure what I did first time around .. I will keep playing with it to see if I can get better results . I'll get back to you . ... From:...
alex
kryer_99
Offline Send Email
Jan 22, 2006
1:12 am
831
OK , I don't think i was picking the right margin of error first time around . Now I am picking 'Stop when 100.0% of validating examples are within 0.2% of...
alex
kryer_99
Offline Send Email
Jan 22, 2006
2:39 am
832
Alex, ... 0.2% is a very tight margin. Can I have a look at the file? If so, send it as an attachment to support@... -- Steve Wolstenholme Neural...
steve@...
easynn
Offline Send Email
Jan 22, 2006
9:51 am
833
Thanks Steve . I sent it over to support@... . Any help appreciated . ... From: steve@... To: easynn@yahoogroups.com Sent: Sunday, January 22,...
alex
kryer_99
Offline Send Email
Jan 22, 2006
5:25 pm
834
Unless you figure something out , I think I have another option ... and that is to change the outputs to whole numbers that would convey the same essential ...
alex
kryer_99
Offline Send Email
Jan 23, 2006
5:18 am
835
... I'm still trying! You can change the grid values by right clicking and setting a function. However, changing the outputs to whole numbers should not make...
steve@...
easynn
Offline Send Email
Jan 23, 2006
9:08 am
836
I can't get any better validating results than 35% within a 1% range. If I try to use your suggested 0.2% range the best I can get is 6.2% validating. Your...
steve@...
easynn
Offline Send Email
Jan 23, 2006
7:29 pm
837
I can't get any better validating results than 35% within a 1% range. If I try to use your suggested 0.2% range the best I can get is 6.2% validating. Your...
steve@...
easynn
Offline Send Email
Jan 24, 2006
2:59 am
838
Well , you said some of my inputs are not useful . I can try to improve that ... And like I said I can manipulate the outputs and with that I can get it up to ...
alex
kryer_99
Offline Send Email
Jan 24, 2006
4:24 am
839
What is acceptable value for Input Importance ? You liked the ones over 30 in my data ... what is the cutoff for bad/good ? ... From: steve@... To:...
alex
kryer_99
Offline Send Email
Jan 24, 2006
6:02 am
840
Alex, I have had a message from Phil. He is happy to run your data through DTREG to see what results he gets. Some problems are better solved with decision...
steve@...
easynn
Offline Send Email
Jan 24, 2006
3:09 pm
841
Hi Steve , You have been very helpful and it is really very appreciated ! Thank You sincerely . ... From: steve@... To: easynn@yahoogroups.com Sent:...
alex
kryer_99
Offline Send Email
Jan 24, 2006
4:24 pm
842
... There is no "acceptable" value. Input Importance shows the importance of each input to the next layer (hidden layer 1). Ideally all inputs should have the...
steve@...
easynn
Offline Send Email
Jan 25, 2006
11:36 am
843
Some e-mail replies to support questions, orders and free upgrade requests are being rejected by badly designed spam detectors. If you are expecting a reply...
steve@...
easynn
Offline Send Email
Jan 25, 2006
11:37 am
844
Many users have requested that the validating error is included on the learning progress graph. It has always been pushed down in the development queue because...
steve@...
easynn
Offline Send Email
Jan 31, 2006
2:32 pm
845
Dear Group Members, We are a group of 3 full-time researchers and 3 part-times ones, mainly from Italy, who are interested in Financial Time Series ...
giuliorugarli
Offline Send Email
Feb 1, 2006
6:14 pm
846
sounds interesting as i am a phd student working on bankruptcy prediction model but my OResearch is slightly weak pls identify(roughly) the area for me so that...
HATHI
uttamhathi1717
Offline Send Email
Feb 2, 2006
3:48 pm
Messages 817 - 846 of 1554   Oldest  |  < Older  |  Newer >  |  Newest
Advanced
Add to My Yahoo!      XML What's This?

Copyright © 2009 Yahoo! Inc. All rights reserved.
Privacy Policy - Terms of Service - Guidelines - Help