支持向量机
极小极大
二元分类
正规化(语言学)
机器学习
估计员
二进制数
人工智能
神经反射
计算机科学
非线性系统
数学
数学优化
统计
心理学
量子力学
算术
精神科
物理
脑电图
作者
Sook Ling Leong,Sven Vanneste,Jinwoong Lim,Mark Smith,Pamela T. Manning,Dirk De Ridder,T. Stoeckl-Drax
标识
DOI:10.1016/j.ijpsycho.2018.07.402
摘要
In this paper, we propose novel second-order cone programming formulations for binary classification, by extending the Minimax Probability Machine (MPM) approach. Inspired by Support Vector Machines, a regularization term is included in the MPM and Minimum Error Minimax Probability Machine (MEMPM) methods. This inclusion reduces the risk of obtaining ill-posed estimators, stabilizing the problem, and, therefore, improving the generalization performance. Our approaches are first derived as linear methods, and subsequently extended as kernel-based strategies for nonlinear classification. Experiments on well-known binary classification datasets demonstrate the virtues of the regularized formulations in terms of predictive performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI