loglikelihood does not involve W anywhere, so the derivative is zero. The
reason is that the object Zl and Sl that you introduced have nothing to do
with Zk and Sk that were computed earlier, they share the name but are of a
different class. Other issues:
Since you are using passive forms Sum
Dear All,
I would like to take the derivative symbolically of a function but it
doesn't seem to work. Basically W and S are matrices, Z=f(W,S) and
loglikelihood=f(eta,Z). I would like the partial derivatives of the
loglikelihood wrt eta and W_ij. It works for eta but not the W_ij. Here is
the
Howdy again,
I am going to submit the tutorial proposal by the end of the day today. We
have Aaron, Kenny, Ben, and me signed up to teach this.
If you have any comments or edits, please let me know or make them in the
next several hours.
https://github.com/sympy/sympy/wiki/SciPy-2018-Tutorial-Pr
