| 神经网络极速学习方法研究 |
| |
| 引用本文： | 邓万宇,郑庆华,陈琳,许学斌.神经网络极速学习方法研究[J].计算机学报,2010,33(2). |
| |
| 作者姓名： | 邓万宇 郑庆华 陈琳 许学斌 |
| |
| 作者单位： | 1. 西安交通大学电信学院计算机系智能网络与网络安全教育部重点实验室,西安,710049
2. 西安邮电学院计算机科学与技术系,西安,710061 |
| |
| 基金项目： | 国家自然科学基金(60825202,60803079,60633020);;国家“八六三”高技术研究发展计划项目基金(2008AA01Z131);;国家科技支撑计划项目(2006BAK11B02,2006BAJ07B06,2008BAH26B02,2009BAH51B00);;中国科学院复杂系统与智能研究科学重点实验室开放基金资助项目(20080101);;陕西省教育厅科学研究计划项目(09JK717)资助 |
| |
| 摘 要： | 单隐藏层前馈神经网络(Single-hidden Layer Feedforward Neural Network,SLFN)已经在模式识别、自动控制及数据挖掘等领域取得了广泛的应用,但传统学习方法的速度远远不能满足实际的需要,成为制约其发展的主要瓶颈.产生这种情况的两个主要原因是:(1)传统的误差反向传播方法(Back Propagation,BP)主要基于梯度下降的思想,需要多次迭代;(2)网络的所有参数都需要在训练过程中迭代确定.因此算法的计算量和搜索空间很大.针对以上问题,借鉴ELM的一次学习思想并基于结构风险最小化理论提出一种快速学习方法(RELM),避免了多次迭代和局部最小值,具有良好的泛化性、鲁棒性与可控性.实验表明RELM综合性能优于ELM、BP和SVM.
|
| 关 键 词： | 极速学习机 正则极速学习机 支持向量机 结构风险 神经网络 最小二乘 |
Research on Extreme Learning of Neural Networks |
| |
| DENG Wan-Yu,ZHENG Qing-Hua,CHEN Lin,XU Xue-Bin.Research on Extreme Learning of Neural Networks[J].Chinese Journal of Computers,2010,33(2). |
| |
| Authors: | DENG Wan-Yu ZHENG Qing-Hua CHEN Lin XU Xue-Bin |
| |
| Affiliation: | Ministry of Education Key Laboratory for Intelligent Networks and Network Security/a>;Department of Computer Science and Technology/a>;Xi'an Jiaotong University/a>;Xi'an 710049;Department of Computer Science and Technology/a>;Xi'an University of Posts & Telecommunications/a>;Xi'an 710121 |
| |
| Abstract: | SLFNs(Single-hidden Layer Feed forward Neural networks)have been widely applied in many fields including pattern recognition,automatic control,data mining etc.However,the traditional learning methods can not meet the actual needs due to two main reasons.Firstly,the traditional method is mainly based on gradient descent and it needs multiple iterations.Secondly,all of the network parameters need to be determined by iteration.Therefore,the computational complexity and searching space will increase dramaticall... |
| |
| Keywords: | extreme learning machine regularized extreme learning machine support vector machine structural risk neural network least square |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
