Skip to main content
. Author manuscript; available in PMC: 2016 Sep 1.
Published in final edited form as: Neural Comput. 2015 Jun 16;27(9):1825–1856. doi: 10.1162/NECO_a_00759

Algorithm 1.

ECME algorithm to learn TD-GPFA model parameters

Initialize θ0;
n ← 1;
repeat
graphic file with name nihms693539t1.jpg   E-step: Compute P(X|Y) according to θn;
  CM-step 1: Define g1n) = {vec(Dn)} and maximize
  fn) = E[log P(X, Yn)] wrt θn keeping g1n) fixed;
  CM-step 2: Define g2(θn)={vec(Cn),dn,diag(Rn),τ1nτpn} and
  maximize Ln) = P(Yn) wrt θn keeping g2n) fixed;
  nn + 1
until θn has converged or n = max number of iterations;