Handling Over-fitting and Class-imbalance Jointly in Pittsburgh LCS

ISBN-13: 9783659596568 / Angielski / Miękka / 2017 / 100 str.

Shubhra Kanti Karmaker Santu; Md. Monirul Islam

Opis

Generalization ability of a classi er is an important issue for any classification task. Two prominent problems affecting the generalization ability are over- tting and class-imbalance. This book presents a new evolutionary system, i.e., EDARIC, for rule induction and classi cation. The evolutionary approach used in our new system is based on a destructive method that starts with large-sized rules and gradually decreases the sizes as evolution progresses. The experimental results show that our proposed evolutionary system obtains better generalization performance compared to the existing algorithms.

O autorze

Shubhra is a third Year PhD student at University of Illinois Urbana-Champaign. His research interest lies at the intersection of information retrieval and text mining. He also worked as research intern at Microsoft Research, Yahoo research and WalmartLabs.