ExpertBayes: Automatically refining manually built Bayesian networks
This work addresses the need for efficient refinement of expert knowledge in domains like medicine, though it is incremental as it builds on existing manual network construction.
The paper tackled the problem of improving manually built Bayesian networks by showing that minor perturbations to expert-constructed structures can yield better classifiers with very small computational cost, while preserving most of the original model's intended meaning.
Bayesian network structures are usually built using only the data and starting from an empty network or from a naive Bayes structure. Very often, in some domains, like medicine, a prior structure knowledge is already known. This structure can be automatically or manually refined in search for better performance models. In this work, we take Bayesian networks built by specialists and show that minor perturbations to this original network can yield better classifiers with a very small computational cost, while maintaining most of the intended meaning of the original model.