Dissertation > Excellent graduate degree dissertation topics show

Small-World Architecture Based Kernel Auto-associative Memory Framework and Its Applications

Author: ChenLei
Tutor: ChenSongCan
School: Nanjing University of Aeronautics and Astronautics
Course: Computer Software and Theory
Keywords: artificial neural networks associative memory kernel method small-world architecture sparse network structure or architecture face recognition
CLC: TP183
Type: Master's thesis
Year: 2005
Downloads: 124
Quote: 0
Read: Download Dissertation

Abstract


This thesis mainly focuses on a small-world architecture based kernel auto-associative memory framework and its applications on small scale face recognition, specifically including how to construct a unified framework of conventional auto-associative memory models, how to reduce complexity of fully-connected models and the unified framework’s application on face recognition. Some recent research theories, such as the popular “kernel method” in machine learning and extensively existed “small world network” in social fields, are applied to auto-associative memory models. Main contributions of this thesis are summarized as follows: Firstly, a unified framework of kernel auto-associative memory models is constructed and developed. In this thesis, based on Hopfield associative memory model, the author proposes a framework of kernel auto-association memory models by using the kernel trick to directly modify its recall (update) rules. With such a framework, we can not only uniformly formulate the existing auto-associative memory models but also derive more new different models using different kernels from the framework. Secondly, the complexity of fully-connected kernel auto-associative memory models is reduced. At present, almost all the auto-associative memory models adopt full-connected structure or architecture. With the real demands and the enlarging of the scale of handled problem, the complexity of the models have increased greatly, which will undoubtedly result in the difficulty of connecting up on the craft, and restrict models’ circuit implementation. The research results in this thesis show that, compared with the regular network and random network, introducing small-world architecture into kernel auto-associative memory models is confirmed to be more effective. Finally, a series of novel face recognition algorithms based on associative memory models are proposed. On the basis of aforesaid work, the author further proposes robust face recognition algorithms based on sparse kernel auto- associative memory models. Simulation results on a part of the FERET face image database show that these algorithms not only achieve almost the same recognition performance as that of fully-connected models, but also outperform both famous Eigenfaces and (PC)2A algorithms after adding random noise or occluding partially on face image.

Related Dissertations

  1. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  2. Research on Algorithms of 2D Face Template Protection,TP391.41
  3. Research of Anomaly Detection Algorithms of Hyperspectral Imagery Based on Kernel Method,TP751
  4. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  5. Research of Video Face Recognition Based on Weighted Voting and Key-Frame Extraction,TP391.41
  6. Face Recognition Method Based on DE,TP391.41
  7. A Novel Approach for Projection by Optimize Local Area in Face Recognition Applications,TP391.41
  8. The Research and System Design of Assessment Model for Network Learning Based on Intelligent Computation,TP18
  9. Research on Deep Structure Learning Algorithms Based on Dynamic Fuzzy Relation,TP181
  10. Predicting Short-term Foreign Exchange Based on Wavelet Neural Network,F224
  11. The Research for Face Recognition Based on Pseudo-Zernike Moment and BP Network,TP391.41
  12. Research about Cognitive Model of Rumors Based o Hopfield Neural Network,B842.1
  13. Helicopter main gearbox fault diagnosis and failure prediction technology research,V267
  14. Based on sparse representation Face Image Recognition Method,TP391.41
  15. Research and Implementation of Website Code Recognition Based on RPROP Artificial Neural Network,TP393.08
  16. The Neural Network Digital Watermarking Algorithm,TP309.7
  17. Face Recognition Based on Optimized Bayesian Method,TP391.41
  18. Tobacco Leaf Detection System Research and Application Based on Image Processing and Artificial Neural Network,TP274
  19. Research of Face Recognition Technology Applicated in Access Control System,TP273.5
  20. Research on the Application of Face Recognition Technology in the Intelligent Robot,TP242.6
  21. Word Sense Disambiguation of English Modal Verb Will by Support Vector Machines,H313

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