Gneural Network - Tasks: task #14135, Support direct partial derivative...
You are not allowed to post comments on this tracker with your current authentication level.
task #14135: Support direct partial derivative functions.
Submitter: | Ray Dillinger <rayd> | ||
Submitted: | Sat 27 Aug 2016 01:09:54 AM UTC | ||
Should Start On: | Fri 26 Aug 2016 07:00:00 AM UTC | Should be Finished on: | Mon 26 Sep 2016 07:00:00 AM UTC |
Category: | None | Priority: | 5 - Normal |
Status: | None | Privacy: | Public |
Assigned to: | None | Percent Complete: | 0% |
Open/Closed: | Open | Effort: | 0.00 |
No files currently attached
Depends on the following items: None found
Items that depend on this one: None found
Carbon-Copy List
There are 0 votes so far. Votes easily highlight which items people would like to see resolved in priority, independently of the priority of the item set by tracker managers.
Follow 2 latest changes.
Date | Changed by | Updated Field | Previous Value | => | Replaced by |
---|---|---|---|---|---|
2016-08-27 | rayd | Should be Finished on | 2016-08-26 | 2016-09-26 | |
2016-08-27 | rayd | Carbon-Copy | - | Added -email is unavailable- |
Powered by Savane 3.13-02a9.
Corresponding source code
The method of computing partial derivatives currently expressed in the code is inaccurate (the interval is sufficiently small that shallow gradients will sometimes be rounded to zero, and if made larger it will sometimes span topologically important features in the fitness space).
It is also inefficient (requires multiple calls to the activation function).
Both things can be fixed by using explicit derivative functions which need be called only once.