Comak E, Arslan A
Department of Computer Engineering, Engineering and Architecture Faculty, Selcuk University, Konya, Turkey.
J Med Eng Technol. 2006 Mar-Apr;30(2):73-7. doi: 10.1080/03091900500095729.
Support vector machines can be used in a new machine learning technique based on statistical learning. In this paper, we develop least squares support vector machines (LS-SVMs) using the lazy learning approach to classify data in unclassifiable regions in the case of multi-class classification. LS-SVMs use a set of linear equations while SVMs use a quadratic programming problem. The lazy learning approach is a local and memory-based technique. Therefore, it is an alternative technique to fuzzy inference systems. Our studies show that LS-SVMs with the lazy learning approach can give comparable results to fuzzy LS-SVMs for multi-class classification.
支持向量机可用于基于统计学习的一种新的机器学习技术。在本文中，我们使用懒惰学习方法开发最小二乘支持向量机（LS - SVM），以便在多类分类情况下对不可分类区域中的数据进行分类。LS - SVM使用一组线性方程，而支持向量机使用二次规划问题。懒惰学习方法是一种基于局部和内存的技术。因此，它是模糊推理系统的一种替代技术。我们的研究表明，采用懒惰学习方法的LS - SVM在多类分类方面能够给出与模糊LS - SVM相当的结果。
