arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1205.4698cs.LG
收藏

权值收缩在大间隔感知机学习中的作用

The Role of Weight Shrinking in Large Margin Perceptron Learning

Aristotle University of Thessaloniki(塞萨洛尼基亚里士多德大学)

Constantinos Panagiotakopoulos, Petroula Tsampouka

摘要:

我们引入到经典的感知器算法与利润率的机制,缩小当前的权重向量作为第一步的更新。如果收缩因子是常数,则所得到的算法可以被视为具有常数学习率的NORMA的边缘误差驱动版本。在这种情况下,我们表明,允许的收缩强度取决于最大余量的值。我们还考虑变量收缩因子,没有这样的依赖。在这两种情况下,我们得到新的广义的感知器与利润能够证明达到在有限数量的步骤中的任何理想的近似的最大利润超平面。新的近似最大间隔分类实验上出现的2范数软利润率任务,涉及线性内核是非常有竞争力的。

英文摘要:

We introduce into the classical perceptron algorithm with margin a mechanism that shrinks the current weight vector as a first step of the update. If the shrinking factor is constant the resulting algorithm may be regarded as a margin-error-driven version of NORMA with constant learning rate. In this case we show that the allowed strength of shrinking depends on the value of the maximum margin. We also consider variable shrinking factors for which there is no such dependence. In both cases we obtain new generalizations of the perceptron with margin able to provably attain in a finite number of steps any desirable approximation of the maximal margin hyperplane. The new approximate maximum margin classifiers appear experimentally to be very competitive in 2-norm soft margin tasks involving linear kernels.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑