• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Li, Meng (Li, Meng.) | Li, Wenjing (Li, Wenjing.) | Qiao, Junfei (Qiao, Junfei.)

收录:

EI Scopus SCIE

摘要:

Being a commonly used way for task decomposition in modular neural network (MNN), clustering analysis is employed to decompose the complex task into several simple subtasks for learning. Recent studies mainly focus on hard clustering, but the clusters might be not sufficiently represented when the cluster boundary is ambig-uous, which may degenerate the learning performance of subnetworks in MNN. To solve this problem, we design a modular neural network based on an improved soft subspace clustering (IESSC-MNN) algorithm in this study. Firstly, we propose an improved soft subspace clustering algorithm for task decomposition in MNN, which di-vides the original space into several interactive feature subspaces and allocates a weight item to each subspace to describe the contribution of the subtasks at the same time. Secondly, each RBF subnetwork is adaptively con-structed using a structure growing strategy, and all subnetworks learning the corresponding subtask in parallel. Finally, all subnetworks' outputs are integrated by weighted summation using the contribution weight of sub-networks. The simulation results of the proposed model on five benchmark data and a practical dataset indicate that IESSC-MNN improves the modeling accuracy and generalization performance with a simple structure when compared with other MNNs.

关键词:

Soft subspace clustering Modular neural network Improved second-order algorithm RBF neural network

作者机构:

  • [ 1 ] [Li, Meng]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Li, Wenjing]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Qiao, Junfei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Li, Meng]Beijing Lab Computat Intelligence & Intelligent Sy, Beijing 100124, Peoples R China
  • [ 5 ] [Li, Wenjing]Beijing Lab Computat Intelligence & Intelligent Sy, Beijing 100124, Peoples R China
  • [ 6 ] [Qiao, Junfei]Beijing Lab Computat Intelligence & Intelligent Sy, Beijing 100124, Peoples R China
  • [ 7 ] [Li, Meng]Beijing Lab Smart Environm Protect, Beijing 100124, Peoples R China
  • [ 8 ] [Li, Wenjing]Beijing Lab Smart Environm Protect, Beijing 100124, Peoples R China
  • [ 9 ] [Qiao, Junfei]Beijing Lab Smart Environm Protect, Beijing 100124, Peoples R China
  • [ 10 ] [Li, Meng]Minist Educ, Engn Res Ctr Intelligent Percept & Autonomous Cont, Beijing 100124, Peoples R China
  • [ 11 ] [Li, Wenjing]Minist Educ, Engn Res Ctr Intelligent Percept & Autonomous Cont, Beijing 100124, Peoples R China
  • [ 12 ] [Qiao, Junfei]Minist Educ, Engn Res Ctr Intelligent Percept & Autonomous Cont, Beijing 100124, Peoples R China
  • [ 13 ] [Li, Meng]Beijing Inst Artificial Intelligence, Beijing 100124, Peoples R China
  • [ 14 ] [Li, Wenjing]Beijing Inst Artificial Intelligence, Beijing 100124, Peoples R China
  • [ 15 ] [Qiao, Junfei]Beijing Inst Artificial Intelligence, Beijing 100124, Peoples R China
  • [ 16 ] [Qiao, Junfei]100 Pingleyuan, Beijing 100124, Peoples R China

通讯作者信息:

查看成果更多字段

相关关键词:

来源 :

EXPERT SYSTEMS WITH APPLICATIONS

ISSN: 0957-4174

年份: 2022

卷: 209

8 . 5

JCR@2022

8 . 5 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:49

JCR分区:1

中科院分区:1

被引次数:

WoS核心集被引频次: 8

SCOPUS被引频次: 12

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:485/4948239
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司