Taboo Order
Context
- The Taboo Order learning method uses Taboo search in the space of the order of the Bayesian network nodes.
- Finding the best Bayesian network for a fixed node order is an task that consists of choosing the parents of a node among the nodes that appear before it in the given order.
- This is the more comprehensive search method compared to the Taboo algortithm, but also more time consuming.
- Fixed Arcs are considered normal arcs in this context, but Forbidden Arcs and Temporal Indices are taken into account.
- In addition to the standard learning options, you can define the size of the taboo list for Taboo Order learning.