When Ensemble Learning Meets Deep Learning: a New Deep Support Vector Machine for Classification
作者：
Highlights：
• Focusing on the DL research based on Support Vector Machine (SVM).
• First give an Ex-Adaboost learning strategy.
• Proposing a new Deep Support Vector Machine (called DeepSVM).
• Using Ex-Adaboost to not only select SVMs with the minimal error rate and the biggest diversity, but also give each feature’s weight for the new training data.
• Obtaining a new set of deep features that can been classified more easily.
• Entering training data represented by these new features into a standard SVM.
摘要
•Focusing on the DL research based on Support Vector Machine (SVM).•First give an Ex-Adaboost learning strategy.•Proposing a new Deep Support Vector Machine (called DeepSVM).•Using Ex-Adaboost to not only select SVMs with the minimal error rate and the biggest diversity, but also give each feature’s weight for the new training data.•Obtaining a new set of deep features that can been classified more easily.•Entering training data represented by these new features into a standard SVM.
论文关键词：Pattern recognition,Deep architectures,Support vector machine
论文评审过程：Received 10 November 2015, Revised 9 March 2016, Accepted 28 May 2016, Available online 30 May 2016, Version of Record 9 July 2016.
论文官网地址：https://doi.org/10.1016/j.knosys.2016.05.055
