Recently, some community focuses on computer aided engineering inductive applications, as seen in workshops, such as AAAI98/ICML98
workshop on ‘The Methodology of Applying Machine Learning’ and ECML98 workshop on ‘Upgrading Learning to the Meta-level: Model
Selection and Data Transformation‘. It is time to decompose inductive learning algorithms and organize inductive learning
methods (ILMs) for reconstructing inductive learning systems. Given such ILMs, we may invent a new inductive learning system
that works well to a given data set by re-interconnecting ILMs