1) Hierarchical Fusion Method for Recognition
层次化融合识别方法
2) feature-level fusion recognition
特征层融合识别
1.
The global-adaptive BP algorithms have the shortcomings of converging slowly and learning unstably in feature-level fusion recognition.
针对特征层融合识别中全局自适应BP算法存在的收敛速度慢、学习不稳定等问题,基于对动量BP算法的详细分析,提出了一种新的全局自适应BP算法——回弹全局自适应动量BP算法(RGMOBP),该算法具有在误差增大时进行权值回弹并减小学习步长以保证权值的调节功能、使误差减小的特点。
3) decision-level identification fusion
决策层融合识别
4) Multi-levels fusion
层次化融合
5) hierarchical topic detection
层次化话题识别
1.
Topic detection and tracking (TDT) aims to develop a series of technologies for event based information organization, and hierarchical topic detection (HTD) is a new task of it.
话题识别与跟踪(topic detection and tracking,TDT)旨在发展一系列基于事件的信息组织技术,层次化话题识别(hierarchical topic detection,HTD)是其中一项全新的任务定义形式。
6) hierarchy recognition
层次识别
1.
A form feature hierarchy recognition method based on knowledge and graph is proposed to solve the problem of available management of relationship among features.
为解决特征识别中对特征间关系缺乏有效处理的问题,提出基于知识与图的形状特征层次识别方法。
补充资料：公理化方法(见公理化和形式化)
公理化方法(见公理化和形式化)
axiomatical method
gongllbuafangfa公理化方法化和形式化。(axiomatieal method)见公理
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条