Deterministic annealing EM algorithm

Naonori Ueda, Ryohei Nakano, 1998.

Voynich ManuscriptArticledoi: 10.1016/S0893-6080(97)00133-00

What it's used for here

Neural Networks 11(2): 271-282 (bibliographic record with DOI checked on researchr.org). EM with the posterior computed from p(x, z) raised to a power beta that rises to 1, to escape poor local optima. Used in T41 generation 4 after the diagnostic showed the true key's basin has higher likelihood than any random restart.

Cited by on this site 2 records

Population-annealed EM for the lattice key, compared with independent restarts

Method

MTH

The Voynich Manuscript

The mystery article

MYS

Cite it

Naonori Ueda, & Ryohei Nakano (1998). Deterministic annealing EM algorithm. https://doi.org/10.1016/S0893-6080(97)00133-0

@article{ueda1998deterministic,
  author = {Naonori Ueda} and {Ryohei Nakano},
  title = {Deterministic annealing EM algorithm},
  year = {1998},
  doi = {10.1016/S0893-6080(97)00133-0}
}

TY  - JOUR
TI  - Deterministic annealing EM algorithm
AU  - Naonori Ueda
AU  - Ryohei Nakano
PY  - 1998
DO  - 10.1016/S0893-6080(97)00133-0
ER  -

and . “Deterministic annealing EM algorithm.” 1998. https://doi.org/10.1016/S0893-6080(97)00133-0.