Thread Tools
This thread is privately moderated by Jack Crossfire, who may elect to delete unwanted replies.
Oct 10, 2007, 12:39 PM
Registered User
Jack Crossfire's Avatar
Thread OP

Cube algorithm

The neural network training doesn't represent the full range of angles & accelerations well. It only trains on the most recent samples, regardless the range they happen 2 B in. Wouldn't it be nice to have angles in each range, regardless of time.

Tried using a table of most recent angle->accel slots in every range. The result of this was horrible. The correlation seems too erratic to derive from anything but the most recent samples, but it's an intriguing algorithm to keep around.

Now we have a strange phenomenon where more training iterations make the network less reliable.

With the rainy season underway and much more money on the airframe than last year, we're rained out indefinitely.
Last edited by Jack Crossfire; Oct 10, 2007 at 12:48 PM.
Sign up now
to remove ads between posts
Oct 10, 2007, 05:11 PM
Too little play time...
WarrrEagle!'s Avatar
Sometimes I fear you are passing coded messages to our enemies...

Just sayin'.

Quick Reply
Thread Tools