【24h】

Introduction

机译:介绍

获取原文
获取原文并翻译 | 示例
           

摘要

The International Conference on Neural Information Processing (ICONIP) is a prestigious event organized by regional active academicians to explore and exchange ideas on neural networks and related disciplines since 1994. The ICONIP2006 covers topics on neural network theory and models, computational neuroscience and cognitive science, hybrid systems and hardware, and neural network applications. In this special issue of Journal of Intelligent Information Systems, we have invited two original papers from ICONIP that highlight the research in neural networks.rnBan et al. present the multi-manifold partition method to identify the interlacing low dimensional patterns from high dimensional data space. A neighbourhood graph is utilized to capture the topological structure. Primary structures searching and merging algorithms are developed to estimate the dimensionalities of the vectors in the neighbourhood graph, unite the connected vectors with the same dimensionality and merge primary structures.
机译:自1994年以来,国际神经信息处理大会(ICONIP)是由地区活跃的学者组织的一次著名活动,旨在探讨和交流有关神经网络和相关学科的思想。ICONIP2006涵盖了有关神经网络理论和模型,计算神经科学和认知科学,混合系统和硬件以及神经网络应用程序。在本期《智能信息系统杂志》上,我们邀请了ICONIP的两篇原创论文,重点介绍了神经网络方面的研究。提出了一种多歧管分割方法,用于从高维数据空间中识别隔行扫描的低维模式。利用邻域图来捕获拓扑结构。开发了主要结构搜索和合并算法,以估计邻域图中向量的维数,将连接的向量与相同维数合并,并合并主要结构。

著录项

  • 来源
  • 作者单位

    Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, People's Republic of China;

    Department of Systems Engineering and Engineering Management, William M. V. Mong Engineering Building, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, People's Republic of China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号