arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.03148cs.LGstat.ML
收藏

寻找最小VC维分类器的神经动力学系统

A Neurodynamical System for finding a Minimal VC Dimension Classifier

Indian Institute of Technology Delhi(德里印度理工学院);Federal University of Rio de Janeiro(里约热内卢联邦大学)

Jayadeva, Sumit Soman, Amit Bhaya

摘要:

最近提出的最小复杂性机器(MCM)通过最小化Vapnik-Chervonenkis(VC)维度上的精确边界来找到超平面分类器。VC维度量学习机的能力,较小的VC维导致改进的泛化。在许多基准数据集上,MCM比SVM更好地推广,并且使用的支持向量比SVM使用的支持向量少得多。在本文中,我们描述了一个基于线性动力系统的神经网络,收敛到MCM解决方案。所提出的MCM动力系统有利于在芯片上实现模拟电路或使用常微分方程(ODE)求解器进行仿真。在UCI数据库的基准数据集上进行的数值实验表明,该方法具有可扩展性和准确性,因为我们使用MCM动力系统获得了更高的精度和更少的支持向量(减少高达74.3%)。

英文摘要:

The recently proposed Minimal Complexity Machine (MCM) finds a hyperplane classifier by minimizing an exact bound on the Vapnik-Chervonenkis (VC) dimension. The VC dimension measures the capacity of a learning machine, and a smaller VC dimension leads to improved generalization. On many benchmark datasets, the MCM generalizes better than SVMs and uses far fewer support vectors than the number used by SVMs. In this paper, we describe a neural network based on a linear dynamical system, that converges to the MCM solution. The proposed MCM dynamical system is conducive to an analogue circuit implementation on a chip or simulation using Ordinary Differential Equation (ODE) solvers. Numerical experiments on benchmark datasets from the UCI repository show that the proposed approach is scalable and accurate, as we obtain improved accuracies and fewer number of support vectors (upto 74.3% reduction) with the MCM dynamical system.

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。

↑