Multiplicative Factorization of Noisy-Max
This work addresses a bottleneck in probabilistic reasoning for medical diagnosis, offering a practical solution for complex networks.
The paper tackles the problem of efficient inference in Bayesian networks using noisy-max, presenting a new representation that enables exact inference in large medical networks like QMR-DT and CPCS, where previous methods failed.
The noisy-or and its generalization noisy-max have been utilized to reduce the complexity of knowledge acquisition. In this paper, we present a new representation of noisy-max that allows for efficient inference in general Bayesian networks. Empirical studies show that our method is capable of computing queries in well-known large medical networks, QMR-DT and CPCS, for which no previous exact inference method has been shown to perform well.