Classification methods and inductive learning rules: what we may learn from theory

• Published in: IEEE transactions on human-machine systems 2006-09, Vol.36 (5), p.649-655
• Main Authors: Alippi, C., Braione, P.
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithm design and analysis; Applied sciences; Artificial intelligence; Classification; Classification algorithms; Computer science; control theory; systems; Control theory. Systems; Cybernetics; Data mining; Electrical equipment industry; Exact sciences and technology; Image classification; Industrial training; Intelligent networks; Intelligent systems; Learning; Learning systems; Mathematical models; Messages; Minimization methods; Miscellaneous; Modelling and identification; Monitoring; neural networks; Optimization; pattern classification; Pattern recognition. Digital image processing. Computational geometry; Readers
• ISSN: 1094-6977; 2168-2291; 1558-2442; 2168-2305
• DOI: 10.1109/TSMCC.2005.855508

Inductive learning methods allow the system designer to infer a model of the relevant phenomena of an unknown process by extracting information from experimental data. A wide range of inductive learning methods is nowadays available, potentially ensuring different levels of accuracy on different problem domains. In this critical review of theoretic results gained in the last decade, we address the problem of designing an inductive classification system with optimal accuracy when domain knowledge is limited and the number of available experiments is-possibly-small. By analyzing the formal properties of consistent learning methods and of accuracy estimators, we wish to convey to the reader the message that the common practice of aggressively pursuing error minimization with different training algorithms and classification families is unjustified