A Framework for Control Strategies in Uncertain Inference Networks
This work addresses control strategy design for uncertain inference networks, but it appears incremental as it builds on existing concepts like staged look-ahead without demonstrating broad SOTA impact.
The paper tackles the problem of control strategies in hierarchical probabilistic inference networks by formalizing strategies using the Depth Vector concept and illustrating them on three-level trees. The result is INFERENTI, a Prolog-based system that simulates test data and compares average performance across strategies.
Control Strategies for hierarchical tree-like probabilistic inference networks are formulated and investigated. Strategies that utilize staged look-ahead and temporary focus on subgoals are formalized and refined using the Depth Vector concept that serves as a tool for defining the 'virtual tree' regarded by the control strategy. The concept is illustrated by four types of control strategies for three-level trees that are characterized according to their Depth Vector, and according to the way they consider intermediate nodes and the role that they let these nodes play. INFERENTI is a computerized inference system written in Prolog, which provides tools for exercising a variety of control strategies. The system also provides tools for simulating test data and for comparing the relative average performance under different strategies.