Contribution to attributive and object subcontexts in inferring good maximally redundant tests

Abstract The paper is devoted to inferring a special kind of classification logical rules called good maximally redundant classification tests (GMRTs). They are good because they cover the largest possible number of objects w.r.t. the inclusion relation on the set of all object subsets. Two kinds of classification subcontexts are defined: attributive and object ones. The rules of forming and reducing subcontexts based on the notion of essential attributes and objects are given. The context decomposition leads to a mode of incremental learning GMRTs. Four cases of incremental learning are proposed: adding a new object (attribute value) and deleting an object (attribute value). Some heuristic rules, which allow us to decrease the number of subcontexts involved in searching for GMRTs, are proposed too.