Subject:
|
Re: ANN
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Thu, 24 Nov 2005 16:32:48 GMT
|
Viewed:
|
1100 times
|
| |
|
|
| |
Has anyone got an NQC implementation of the signoid function???
|
Actually scrap that - the ANN would have to be trained on the PC (in any
language) with the robot collecting the training data and sending it back.
After training, the ANN would be programmed in NQC and downloaded to the robot
to identify a shape.
Thomas
|
|
Message has 1 Reply:
 | | Re: ANN
|
| (...) Double scrap that - the sigmoid would still be needed in the programmed ANN to be downloaded to the RCX. (19 years ago, 26-Nov-05, to lugnet.robotics, FTX)
|
Message is in Reply To:
| | Re: ANN
|
| (...) With only 3 inputs, there's probably little justification for using an ANN in a Robot, but that's no reason not to try. The most obvious application is categorising something the robot somes into contact with. My son has 3 blocks - green cube, (...) (19 years ago, 24-Nov-05, to lugnet.robotics, FTX)
|
4 Messages in This Thread:
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
