You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have a branch ready that uses exp(x) instead of sin(x) as the y (target) variable. The reason for this is faster and clearer convergence, since exp(x) is well approximated by a Taylor expansion around the origin. Also, all the derivatives are exp(0)=1, so the polynomial coefficients are trivial (1/n! for the n-th term).
I think this is a minor but positive improvement for someone new trying to kick the tires, and experiment with different learning rates, etc.