A boosted SVM classifier trained by incremental learning and decremental unlearning approach

作者：

Highlights：

• Training non-linear SVM is computationally expensive.

• An Efficient SVM training using incremental learning and decremental unlearning.

• A novel boosting algorithm enhances the performance of a non-linear SVM classifier.

• Artificial and real datasets of different sizes, and shapes are tested.

摘要

•Training non-linear SVM is computationally expensive.•An Efficient SVM training using incremental learning and decremental unlearning.•A novel boosting algorithm enhances the performance of a non-linear SVM classifier.•Artificial and real datasets of different sizes, and shapes are tested.

论文关键词：SVM,Boosting,Incremental learning,Decremental unlearning

论文评审过程：Received 16 July 2020, Revised 14 October 2020, Accepted 23 October 2020, Available online 29 October 2020, Version of Record 10 February 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114154