Fast rule representation for continuous attributes in genetics-based machine learning

Genetic-Based Machine Learning Systems (GBML) are comparable in accuracy with other learning methods. However, efficiency is a significant drawback. This paper presents a new representation for continuous attributes motivated by our previous work in large-scale Bioinformatics datasets, where we can observe that, very often, a very small fraction of the attributes of a domain are expressed at the same time in a rule. Automatically discovering these few key attributes and only keeping track of them contributes to a substantial speed up by avoiding useless match operations with irrelevant attributes, while potentially leading to a better learning process. The representation we propose has been tested within the BioHEL GBML system, and our experiments show that this representation has competent learning performance and reduces considerably the system run-time, up to 2-3 times faster than the state-of-the-art in fast GBML representations for datasets with hundreds of attributes. Categorie...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Jaume Bacardit, Natalio Krasnogor
• Keywords: Better Learning Process, GECCO 2008, Irrelevant Attributes, Machine Learning, Optimization