 | | Re: ANN —Thomas Chesney
| | | | (...) 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)
| | | | | | | | | | Re: ANN —Thomas Chesney
| | | | | (...) 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 (...) (19 years ago, 24-Nov-05, to lugnet.robotics, FTX)
| | | | | | | | | | | | Re: ANN —Thomas Chesney
| | | | | (...) 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)
| | | | | | |
