felixpl·há 10 anos·discussInteresting, but I don't understand why you would use anything other than optimal control algorithms for this kind of problem (and determine the feasible directions/positions with neural nets).
felixpl·há 10 anos·discussWeighted least squares should do the trick, i.e. scale your data with the inverse covariance matrix
felixpl·há 10 anos·discussDid you do specific exercises, or just read and re-read Sarno's books to make the concept stick?