Dissertation > Excellent graduate degree dissertation topics show

Study of Supervised Clustering Neural Networks

Author: ChenCong
Tutor: WangShiTong
School: Jiangnan University
Course: Computer Software and Theory
Keywords: Clustering Supervise Radial Basis Function Neural Networks Local modeling Fuzzy Partition Return
CLC: TP183
Type: Master's thesis
Year: 2009
Downloads: 51
Quote: 2
Read: Download Dissertation

Abstract


Clustering is a fundamental technology in the field of artificial intelligence . Traditional unsupervised clustering using manually add the tag information directly on the raw data to be processed , although simple , but often difficult to achieve good results ; while supervised clustering data by using markers to guide the clustering process , can be better results. Radial basis function neural network (Radial Basis Function neural Network, RBFN) is one of the artificial neural network has the advantages of simple structure , good generalization ability , speed , often used in classification, regression and other issues . The RBFN training in traditional unsupervised clustering , in RBFN to introduce supervised clustering proposed supervised clustering neural network based on linear regression model . Traditional the RBF regression modeling of the training data as a whole , and called for global modeling for the local characteristics of the target model approximation accuracy . Local modeling to overcome this defect , but local modeling method is slower and there are boundary effects , this paper using supervised clustering fuzzy partition a new local modeling method , was built according to the different training subset of regression die difficulty of different uses different training algorithm, to eliminate the border effect at the same time to improve the processing speed . This article briefly describes the background such as clustering , RBFN , and then put forward the idea of a supervised clustering algorithm based on linear regression model , the next in RBFN introduction of local modeling and fuzzy partition , and finally through a series of experiments proof of high precision and high efficiency of the method in regression problems .

Related Dissertations

  1. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  2. Research and Implementation of Mining Implicit User Interest,TP311.13
  3. Establishment and Update of Similar Users’ Cluster in Personalized Information Retrieval,TP391.3
  4. Research on Removal Algorithm of Shadows in Image Segmentation,TP391.41
  5. The Research of the Text Extraction Method Based on Spectral Cut,TP391.41
  6. A Pilot Study on Return-to-Work Following Occupational Replantation of Amputated Fingers,R658.1
  7. Gao Zhong-ying academic thought and experience and use of Bufei Decoction treatment of common diseases of the respiratory system drug law,R249.2
  8. Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
  9. The Load Research and Comprehensive Evaluation on the Agricultural Non-Point Source Pollution in Nantong,X592
  10. Research on Clustering Algorithm Based on Mutation Particle Swarm Optimization,TP18
  11. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  12. The Effectiveness of Fiscl Transparency in Supervising Government in China,F812.2
  13. Research on Civil Service Examination System of Anshan City,D630.3
  14. Theory and Practice of Ant Clustering and Partitioning-based DBSCAN Clustering,TP311.13
  15. A Study on Public Budget Supervision of Local Government in China,F812.3
  16. China’s New Rural Cooperative Medical Insurance System Development Problems,R197.1
  17. Commercial banks RMB financial products annualized yield differences research,F832.2
  18. The Loan Pricing Model Based on Risk-Adjusted Return on Capital,F224
  19. Research and Improvement on K-Means Clustering Algorithm,TP311.13
  20. Institutional Investors’ Behavior and Secrities’ Abnormal Returns Study,F832.51;F224
  21. Chaotic Digital Image Encryption Algorithm,TP309.7

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile