Gateway to Think Tanks
来源类型 | Monograph (IIASA Working Paper) |
规范类型 | 论文 |
Exact Classification with Two-Layered Perceptrons. | |
Aarts EHL; Zwietering PJ; Wessels J | |
发表日期 | 1992 |
出版者 | IIASA, Laxenburg, Austria: WP-92-049 |
出版年 | 1992 |
语种 | 英语 |
摘要 | We study the capabilities of two-layered perceptrons for classifying exactly a given subset. Both necessary and sufficient conditions are derived for subsets to be exactly classifiable with two-layered perceptrons that use the hard-limiting response function. The necessary conditions can be viewed as generalizations of the linear-separability condition of one-layered perceptrons and confirm the conjecture that the capabilities of two-layered perceptrons are more limited than those of three-layered perceptrons. The sufficient conditions show that the capabilities of two-layered perceptrons extend beyond the exact classification of convex subsets. Furthermore, we present an algorithmic approach to the problem of verifying the sufficiency condition for a given subset. |
主题 | Methodology of Decision Analysis (MDA) |
URL | http://pure.iiasa.ac.at/id/eprint/3649/ |
来源智库 | International Institute for Applied Systems Analysis (Austria) |
资源类型 | 智库出版物 |
条目标识符 | http://119.78.100.153/handle/2XGU8XDN/124033 |
推荐引用方式 GB/T 7714 | Aarts EHL,Zwietering PJ,Wessels J. Exact Classification with Two-Layered Perceptrons.. 1992. |
条目包含的文件 | ||||||
文件名称/大小 | 资源类型 | 版本类型 | 开放类型 | 使用许可 | ||
WP-92-049.pdf(823KB) | 智库出版物 | 限制开放 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。