I'm a beginner in this topic and are learning how to build an artificial neural network and different types of training associated with them.

Right now, I'm trying to figure out self learning. For example, there is a robot arm consisting of two joints and three parts. The objective is the distance from target (I need the arm to touch the target), neural network inputs are the coordinates of the target, the output is the joint angles of the arm. But, the error is the distance of hand to target.

Since I'm using an error-back-propagation feed-forward neural network, its error is only the output and desired output, but I need it to find the desired output (target joint angle) itself and take the error from distance, not joint angle. How can this be done?

More clearly, what kind of feed-back scheme is there for a back-propagation feed-forward ANN for self-learning of touching a coordinate with robot arm?

  • 1
    $\begingroup$ Related, but not a real answer, have you checked out the work done with the spiking neural networks and arm control by Travis DeWolf? He has a really good research blog that might be helpful. $\endgroup$ – Seanny123 Sep 12 '14 at 15:02
  • $\begingroup$ Looks really impressive. Thanks. $\endgroup$ – huseyin tugrul buyukisik Sep 12 '14 at 15:52
  • $\begingroup$ I think this question is better fitted for either robotics.stackexchange.com, stats.stackexchange.com or ai.stackexchange.com and therefor flagged it as off-topic. $\endgroup$ – awakenting Mar 15 '17 at 19:47
  • $\begingroup$ I'm voting to close this question as off-topic because it is a better fit for mathematics, robotics, stats, ai or another machine learning related stack. $\endgroup$ – Robin Kramer Mar 16 '17 at 15:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.