Novel methods and results in training universal multi-nested neurons

Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications Pub Date : 2002-07-22 DOI:10.1109/CNNA.2002.1035101

R. Dogaru, F. Ionescu, P. Julián, M. Glesner

引用次数: 2

Abstract

This paper presents state of the art methods for training compact universal CNN cells (or neurons) to represent arbitrary local Boolean functions. The design tools are analyzed and optimized such that they are capable to provide fast solutions for cells with more than 4 inputs. In particular, it is proved statistically that any arbitrary Boolean function with n=5 inputs (corresponding to a von Neumann CNN neighborhood) admits multinested cell realizations thus confirming a conjecture that was previously proven only for n<5. Several hints are also provided regarding the choice and the influence of various parameters of the design algorithms on the quality of the solution and the speed of finding it.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

通用多嵌套神经元训练的新方法和结果

本文介绍了训练紧凑通用CNN细胞(或神经元)来表示任意局部布尔函数的最新方法。对设计工具进行了分析和优化，使其能够为具有4个以上输入的细胞提供快速解决方案。特别地，从统计上证明了任何具有n=5个输入(对应于von Neumann CNN邻域)的任意布尔函数都允许多测试的单元实现，从而证实了以前仅在n<5时被证明的猜想。本文还就设计算法的各种参数的选择和对解的质量和求解速度的影响提供了一些提示。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications

自引率

0.00%

发文量

期刊最新文献

Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN) Analogic preprocessing and segmentation algorithms for off-line handwriting recognition Statistical error modeling of CNN-UM architectures: the binary case Realization of couplings in a polynomial type mixed-mode CNN Configurable multi-layer CNN-UM emulator on FPGA