• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on Image Processing: Algorithms and Systems III; 20040119-20040121; San Jose,CA; US >Design of a Universal, Two-Layered Neural Network Derived From the PLI Theory
【24h】

Design of a Universal, Two-Layered Neural Network Derived From the PLI Theory

机译：基于PLI理论的通用两层神经网络的设计

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The if-and-only-if (IFF) condition that a set of M analog-to-digital vector-mapping relations can be learned by a one-layered-feed-forward neural network (OLNN) is that all the input analog vectors dichotomized by the i-th output bit must be positively, linearly independent, or PLI. If they are not PLI, then the OLNN just cannot learn no matter what learning rules is employed because the solution of the connection matrix does not exist mathematically. However, in this case, one can still design a parallel-cascaded, two-layered, perception (PCTLP) to achieve this general mapping goal. The design principle of this "universal" neural network is derived from the major mathematical properties of the PLI theory - changing the output bits of the dependent relations existing among the dichotomized input vectors to make the PLD relations PLI. Then with a vector concatenation technique, the required mapping can still be learned by this PCTLP system with very high efficiency. This paper will report in detail the mathematical derivation of the general design principle and the design procedures of the PCTLP neural network system. It then will be verified in general by a practical numerical example.
机译：可以通过单层前馈神经网络（OLNN）获悉一组M个模数向量映射关系的前提条件（IFF）是所有输入模拟向量被第i个输出位二等分的值必须为正，线性独立或PLI。如果不是PLI，则无论采用什么学习规则，OLNN都将无法学习，因为连接矩阵的解在数学上不存在。但是，在这种情况下，仍然可以设计并行级联的两层感知（PCTLP）来实现此一般映射目标。这种“通用”神经网络的设计原理源自PLI理论的主要数学特性-改变二分输入向量之间存在的依存关系的输出位，以使PLD关系成为PLI。然后，使用向量级联技术，该PCTLP系统仍然可以非常高效地学习所需的映射。本文将详细报告PCTLP神经网络系统的一般设计原理和设计程序的数学推导。然后，将通过一个实际的数值示例大体上对其进行验证。

著录项

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