 |
|
|
|
 |
 |
 |
|
 |
|
 |
|
|
| 陈蕾,陈松灿,张道强.小世界体系的多对多核联想记忆模型及其应用.软件学报,2006,17(2):223-231 |
| 小世界体系的多对多核联想记忆模型及其应用 |
| Small World Structure Inspired Many to Many Kernel Associative Memory Models and Their Application |
| 投稿时间：2005-02-28 修订日期：2005-07-11 |
| DOI： |
| 中文关键词: 神经网络 多对多联想记忆 核方法 小世界理论 智能信息处理 |
| 英文关键词:neural network many to many associative memory kernel trick small world theory intelligent information processing |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.60271017, 60505004 (国家自然科学基金); the Jiangsu Natural Science Foundation of China under Grant No. BK2004001 (江苏省自然科学基金); the Jiangsu Planned Projects for Postdoctoral Research Funds (江苏省博士后科研资助计划) |
| 作者 | 单位 | | 陈蕾 | 南京航空航天大学,计算机科学与工程系,江苏,南京,210016
南京邮电大学,计算机科学与技术系,江苏,南京,210003 | | 陈松灿 | 南京航空航天大学,计算机科学与工程系,江苏,南京,210016 | | 张道强 | 南京航空航天大学,计算机科学与工程系,江苏,南京,210016
计算机软件新技术国家重点实验室,南京大学,江苏,南京,210093 |
|
| 摘要点击次数: 3682 |
| 全文下载次数: 3446 |
| 中文摘要: |
| 运用机器学习中新颖的核方法和社会网络中广泛存在的小世界现象,对Hattori等人提出的多模块多对多联想记忆模型(multi-module associative memory for many-to-many associations,简称(MMA)2)进行了改进,构建出了一个基于小世界体系的多对多核联想记忆模型框架(small world structure inspired many to many kernel associative memory models,简称SWSI-M2KAMs).该框架不仅克服了原模型不能联机提交训练样本且迭代次数过多的缺陷,而且拓展了原模型的智能信息处理范围.更重要的是,通过核函数的选取,该模型框架可以衍生出更多新的多对多联想记忆模型,而且,由于小世界结构的引入,在一定程度上简化了模型的结构复杂度.最后的计算机模拟,证实了新的模型具有良好的多对多联想记忆功能. |
| 英文摘要: |
| Kernel method is an effective and popular trick in machine learning, and small world network is a common phenomenon which exists widely in social fields. In this paper, by introducing them into Hattori et al’s multi-module associative memory for many-to-many associations ((MMA)2), a unified framework of small world structure inspired many-to-many kernel associative memory models (SWSI-M2KAMs) is proposed. The SWSI-M2KAMs not only can store patterns online without more iteration steps, but also extend the range of the processed intelligent information. More importantly, the SWSI-M2KAMs framework can develop more new many-to-many associative memory models by selecting different kernel functions and reduce models’ configuration complexity by using the sparse small world architecture. Finally, computer simulations demonstrate that the constructed models have good performance on many-to-many associative memory. |
|
HTML 下载PDF全文 查看/发表评论 下载PDF阅读器 |
|
|
|
|
|
|
 |
|
|
|
|
 |
|
 |
|
 |
|
