Extending inductive methods to create practical tools for building expert systems

Induction programs make several assumptions that limit their practical utility. Research to overcome the limitation of working within a fixed vocabulary is reported. A recently reported phenomenon in machine learning is that there is a tradeoff between the simplicity of concept descriptions and coverage of training instances, and a learning system cannot have both. It is argued that if a learning system can generate new terms, it can achieve both simplicity and coverage. A method for generating one new kind of terms, comparative terms, is given. The experimental results on a mushroom classification task show that a single comparative term can achieve 90% predictive accuracy