支撑矢量预选取的自适应投影算法

支撑矢量机是一种能在训练样本数很少的情况下达到很好分类推广能力的学习算法。但其在选择支撑矢量时却进行了大量不必要的运算,对此,该文提出了一种能够预选取支撑矢量的方法———自适应投影算法,该方法在不影响支撑矢量机的分类能力情况下,大大地减少了训练样本,提高了支撑矢量机的训练速度。仿真实验结果也验证了该方法的有效性和可行性。

Adaptive Projective Algorithm for Selecting Support Vector Beforehand

Support vector machine is a learning algorithm which has a good classification ability for limited training samples.But support vector machine processes a lot of unnecessary operation s when choosing the support vector.A new method called adaptive projective algorithm which is able to extract support vectors from given training examples is put forward for support vector algorithm.The method greatly reduces the training samples and the runtime of the improved program for support vector machine is shortened compared with the original one,while the classification ability of sup-port vector machine is unaffected.The experimental results show remarkable improvement of speed to support the idea.