EQ

Context

• EQ is an algorithm searching for the equivalence classes of Bayesian networks. This method is very efficient because it avoids local minima and and greatly reduces the size of the search space.
• Like the Taboo learning algorithm, EQ can start with the current network.
• Furthermore, Fixed Arcs are treated as normal arcs, while Forbidden Arcs are taken into account.
• The Temporal Indices are also observed during learning.
• In addition to standard learning options, you can choose to keep the current network structure when starting EQ learning.

References

• P. Munteanu, M. Bendou, The EQ Framework for Learning Equivalence Classes of Bayesian Networks, First IEEE International Conference on Data Mining (IEEE ICDM), San Jose, November 2001.