A new inductive learning algorithm based on monotone system theory

As we know there exist several approaches and algorithms for data mining and machine learning task solution, for example, decision tree learning, artificial neural networks, Bayesian learning, instance-based learning, genetic algorithms, etc. They are effective and well-known and their base algorithms and main ideology are published. In this paper we present a new approach for machine learning (ML) task solution based on Monotone Systems Theory, an inductive learning algorithm named by the authors as MONSIL (MONotone Systems in Inductive Learning). It has some advantages compared with several ML algorithms as rules overlapping, it can use several pruning techniques etc. The base algorithm of MONSIL usually produces more rules than other ML algorithms and it means that it is more work-consuming. We have several effective developments of MONSIL, but to understand them, we must at first present a base algorithm MONSIL. In this paper we define main terms of Monotone Systems Theory, describe a base algorithm, prove that concept description found by MONSIL is complete and consistent, explain algorithm's main steps on an example and also describe the main advantages and disadvantages of this approach.