Search found 55 matches
- Wed 22. Sep 2010, 19:32
- Forum: Scripting
- Topic: Script ETeachResult Data Structure is Defined Where?
- Replies: 3
- Views: 15103
Script ETeachResult Data Structure is Defined Where?
Where is ETeachResult defined? I found the Neuron and Link Data Structure definitions inline in the Edit Neurons Script Section - they were defined after script commands which used them. However, I found ETeachResult used in the GetLastTeachResult() in the Script Teaching Section, however, there was...
- Fri 17. Sep 2010, 21:46
- Forum: Feedback and Suggestions
- Topic: Help > Search Location Column Needs Specifics
- Replies: 1
- Views: 9236
Help > Search Location Column Needs Specifics
Currently, it is difficult to HELP>SEARCH the Script Commands because the HELP>SEARCH LOCATION column always says "MemBrain Help" for any Topics that are found. While the HELP>SEARCH TITLE column brings back the lowest level Heading from the HELP>CONTENTS outline, it is not clear what HELP...
- Thu 16. Sep 2010, 22:25
- Forum: Scripting
- Topic: How to save Best Network?
- Replies: 3
- Views: 15535
Re: How to save Best Network?
...check against the number of epochs being elapsed... I've been searching the script command library and haven't found what call brings back "number of epochs." (I've surely missed it, but I've already spent a couple hours trying to find it.) I was thinking of making a complete list of t...
- Wed 15. Sep 2010, 19:34
- Forum: All about using MemBrain
- Topic: Normalization: How to Control It?
- Replies: 4
- Views: 12640
Re: Normalization: How to Control It?
My question is not about what Normalization is but how its limits are set by Lesson Max/Min or by User spec. I have 3 situations I'm having troubles with: Normalize based on Lesson 1 and then use those limits for Normalizing Lessons 2, 3, 4... Normalize based on Lesson 1 limits, then Normalize on Le...
- Tue 14. Sep 2010, 19:25
- Forum: All about using MemBrain
- Topic: Normalization: How to Control It?
- Replies: 4
- Views: 12640
Re: Normalization: How to Control It?
Any clarification on when Normalization based on Lesson is done when Normalization is checked in the node properties?
- Mon 13. Sep 2010, 19:54
- Forum: Scripting
- Topic: How to save Best Network?
- Replies: 3
- Views: 15535
How to save Best Network?
From what I can tell, the only user control is to specify an error level that when reached, training stops. What would be the best way to do the following conditional stops or saves: Save weights if a new minimum error achieved, Save weights after M epochs have passed (incremental) or on Mth epoch (...
- Tue 24. Aug 2010, 21:36
- Forum: All about using MemBrain
- Topic: Normalization: How to Control It?
- Replies: 4
- Views: 12640
Normalization: How to Control It?
I am having some difficulty controlling Normalization: There are 2 ways I need to control Normalization: Set Normalization Limits and Hold constant for all subsequent lessons. Set Normalization Limits and Reset them for a given New Lesson My biggest confusion is with manually set limits (through the...
- Tue 24. Aug 2010, 20:19
- Forum: All about using MemBrain
- Topic: Normalization, Standardization, etc. of input data
- Replies: 4
- Views: 14507
Re: Normalization, Standardization, etc. of input data
Yes, Standardization is mapping: Mean to Zero Variance to +1 Minus Variance to -1 While this results with a lot of data beyond the [-1,+1] interval, mathematically is presents a variety of advantages when trying to get a non-linear solution. My mathematics degree does not help me much here, but from...
- Fri 20. Aug 2010, 20:13
- Forum: All about using MemBrain
- Topic: Normalization, Standardization, etc. of input data
- Replies: 4
- Views: 14507
Re: Normalization, Standardization, etc. of input data
Thanks for the quick reply! Yes, new training from last known weights is a very good idea since the new solution should be close. Randomization would throw all that away. However, as you said, applying some margin is customary. Any chance that could be incorporated into the Normalization Wizard? (if...
- Wed 18. Aug 2010, 22:40
- Forum: All about using MemBrain
- Topic: Normalization, Standardization, etc. of input data
- Replies: 4
- Views: 14507
Normalization, Standardization, etc. of input data
From what I have gathered so far, there are basically four options for pre-processing input data: Do not pre-process the input data Allow automatic scaling with limits set to the MAX/MIN of the input variable Manually enter the automatic scaling limits. Write script to do any kind of scaling. SITUAT...