| 基于复数权神经元的布尔函数稳健学习算法 |
| |
| 引用本文： | 吕伟锋,林弥,孙玲玲.基于复数权神经元的布尔函数稳健学习算法[J].电子学报,2011,39(11):2708-2712. |
| |
| 作者姓名： | 吕伟锋 林弥 孙玲玲 |
| |
| 作者单位： | 1. 杭州电子科技大学教育部射频电路与系统重点实验室,浙江杭州310018;浙江大学超大规模集成电路设计研究所,浙江杭州310027
2. 杭州电子科技大学教育部射频电路与系统重点实验室,浙江杭州,310018 |
| |
| 摘 要： | 复数权神经元由于引入了多阈值逻辑而具有更强的性能.文中根据其数学模型,结合二进感知器神经元稳健设计概念,提出了该神经元的稳健性数学定义,并根据定义,得到了简单逻辑和异或逻辑的单个神经元稳健实现方案.然后根据该方案提出了任意复杂布尔函数稳健实现算法,同时证明了该算法的正确性.最后通过具体实例演示该算法实现布尔函数的过程和...
|
| 关 键 词： | 复数权值 多值神经元 布尔函数 稳健设计 |
| 收稿时间： | 2009-09-25 |
Robust Learning Algorithm for Boolean Function Based on Neurons with Complex-Valued Weights |
| |
| L Wei-feng,LIN Mi,SUN Ling-ling.Robust Learning Algorithm for Boolean Function Based on Neurons with Complex-Valued Weights[J].Acta Electronica Sinica,2011,39(11):2708-2712. |
| |
| Authors: | L Wei-feng LIN Mi SUN Ling-ling |
| |
| Affiliation: | Lü Wei-feng1,2,LIN Mi1,SUN Ling-ling1(1.Key Laboratory of Ministry of Education for RF Circuits and Systems,Hangzhou Dianzi University,Hangzhou,Zhejiang 310018,China,2.Institute of VLSI Design,Zhejiang University,Zhejiang 310027,China) |
| |
| Abstract: | Neurons with complex-valued weights have a stronger performance due to the multi-threshold logic.In the paper,the robustness for this kind of neurons is presented in accordance with its mathematical model and the binary perceptron's definitions of robustness.The robust design for basic digital logics of multiple variables or XOR logic is proposed after that and the robust algorithm for any Boolean functions base on the neurons is given,also the correctness of the algorithm is proved.The final use of specifi... |
| |
| Keywords: | complex-valued weights multi-valued neurons(MVNs) Boolean function robust design |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
|
