Noise-Tolerant Instance-Based Learning Algorithms

Several published reports show that instancebased learning algorithms yield high classification accuracies and have low storage requirements during supervised learning applications. However, these learning algorithms are highly sensitive to noisy training instances. This paper describes a simple extension of instancebased learning algorithms for detecting and removing noisy instances from concept descriptions. This extension requires evidence that saved instances be significantly good classifiers before it allows them to be used for subsequent classification tasks. We show that this extension's performance degrades more slowly in the presence of noise, improves classification accuracies, and further reduces storage requirements in several artificial and real-world database applications. 1 I n t r o d u c t i o n Instance-based learning (IBL) algorithms have several notable characteristics. They employ simple representations for concept descriptions, have low incremental learning ...

• Type: Conference
• Year: 1989
• Where: IJCAI
• Authors: David W. Aha, Dennis F. Kibler
• Keywords: IJCAI 1989, IJCAI 2007, Instancebased Learning Algorithms, Learning Algorithms, Storage Requirements