Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application
文献类型：会议论文
| 作者 | Wang SJ ; Chen X |
| 出版日期 | 2003 |
| 会议名称 | international joint conference on neural networks |
| 会议日期 | jul 20-24, 2003 |
| 会议地点 | portland, or |
| 关键词 | Pattern Recognition neural networks biomimetic high dimensional geometry |
| 页码 | 2258-2262 |
| 通讯作者 | wang sj chinese acad sci artificial neural networks lab inst semicond pob 912 beijing 100083 peoples r china. |
| 中文摘要 | a new theoretical model of pattern recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical pattern recognition. this new model is closer to the function of human being, rather than traditional statistical pattern recognition using "optimal separating" as its main principle. so the new model of pattern recognition is called the biomimetic pattern recognition (bpr)(1). its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. therefore, it is also called the topological pattern recognition (tpr). the fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. we experimented with the biomimetic pattern recognition (bpr) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. for the total 8800 tests, the correct recognition rate is 99.87%. the rejection rate is 0.13% and on the condition of zero error rates, the correct rate of bpr was much better than that of rbf-svm. |
| 英文摘要 | a new theoretical model of pattern recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical pattern recognition. this new model is closer to the function of human being, rather than traditional statistical pattern recognition using "optimal separating" as its main principle. so the new model of pattern recognition is called the biomimetic pattern recognition (bpr)(1). its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. therefore, it is also called the topological pattern recognition (tpr). the fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. we experimented with the biomimetic pattern recognition (bpr) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. for the total 8800 tests, the correct recognition rate is 99.87%. the rejection rate is 0.13% and on the condition of zero error rates, the correct rate of bpr was much better than that of rbf-svm.; 于2010-10-29批量导入; made available in dspace on 2010-10-29t06:36:29z (gmt). no. of bitstreams: 1 2805.pdf: 297492 bytes, checksum: 768962e1732e50f80432a031c26f9c0f (md5) previous issue date: 2003; int neural network soc.; ieee neural networks soc.; chinese acad sci, artificial neural networks lab, inst semicond, beijing 100083, peoples r china |
| 收录类别 | CPCI-S |
| 会议主办者 | int neural network soc.; ieee neural networks soc. |
| 会议录 | proceedings of the international joint conference on neural networks 2003, vols 1-4
 |
| 会议录出版者 | ieee ; 345 e 47th st, new york, ny 10017 usa |
| 学科主题 | 人工智能 |
| 会议录出版地 | 345 e 47th st, new york, ny 10017 usa |
| 语种 | 英语 |
| ISSN号 | 1098-7576 |
| ISBN号 | 0-7803-7898-9 |
| 源URL | [http://ir.semi.ac.cn/handle/172111/13631]  |
| 专题 | 半导体研究所_中国科学院半导体研究所（2009年前） |
| 推荐引用方式 GB/T 7714 | Wang SJ,Chen X. Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application[C]. 见:international joint conference on neural networks. portland, or. jul 20-24, 2003. |
入库方式： OAI收割
来源：半导体研究所
浏览0
下载0
收藏0
其他版本
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。