Dissertation > Excellent graduate degree dissertation topics show

Study and Application of Dynamic Tunneling Technique in Training of BP Neural Network

Author: LiuJun
Tutor: ZhangYuFang
School: Chongqing University
Course: Computer System Architecture
Keywords: Global optimization BP algorithm Dynamic Tunneling algorithm Multi-trajectory Parallel algorithm
CLC: TP183
Type: Master's thesis
Year: 2005
Downloads: 37
Quote: 2
Read: Download Dissertation

Abstract


The dynamic tunneling algorithm for global optimization has been proposed recently. The dynamic tunneling algorithm is composed of a sequence of cycles. Each cycle includes solving two kinds of dynamical systems: a dynamic optimization system by which a local minimum is found and a dynamic tunneling system by which a new initial solution in a lower valley is determined. The two dynamic systems work alternately to approach a global optimal solution of an objective function.BP (Back Propagation) algorithm is the most popular training algorithm in applications for its non-linear mapping approach capability and robustness. However, it has some defects, such as converging slowly and immersing in local vibration frequently. So an algorithm using dynamic tunneling technique to train BP neural networks has been proposed and has been proved to have good performances.Based on the conventional dynamical tunneling technique, the multi-trajectory dynamic tunneling algorithm has recently been proposed. This algorithm improves search efficiency of the conventional dynamic tunneling system by increasing the trajectories and introducing the interaction between each trajectory of the tunneling system.This paper proposes a new algorithm adopting the multi-trajectory dynamic tunneling technique and the error-limitation dynamic changing technique to train the BP neural networks. The simulation results are provided for three different examples to demonstrate the performance of the proposed method in overcoming the problems of initialization and searching efficiency. The performance of the conventional dynamic tunneling technique and the multi-trajectory dynamic tunneling technique in training BP neural networks are also given and compared in this paper.Moreover, this paper constructs a parallel compute platform to apply the new algorithm by using PC group and PVM virtual system and LINUX OS. On this platform this paper adopts the Master/Slave modal and assigns the data to every computing node to compute. The performance has been provided in the paper.

Related Dissertations

  1. Research on Parallel Frequent Graph Pattern Mining,TP311.13
  2. Intrusion Detection Based on Neural Network Research and Implementation,TP393.08
  3. Study of Parallel Algorithms for Large-Scale Support Vector Machine Problems,TP18
  4. Solution of the Manipulator Inverse Based on Neural Network,TP242
  5. Research on Decoding Algorithm for LDPC Codes,TN911.22
  6. The Research and Application of Neural Network Based on the Maximum Likelihood Method,TP183
  7. Fault Diagnosis for Power Transformer Based on Genetic Algorithm for Optimization of Neural Network,TM407
  8. Study on Parallel Algorithms for Longest Common Subsequence on Heterogeneous Cluster Computing Systems,TP301.6
  9. A Study on the Multi-Population Evolutionary Algorithms for Discrete Variables,TP18
  10. Research of Exchange Rate’s Prediction Method Based on Neural Network,F830.7
  11. Novel Methods for Bioinformatics Applications,TP311.11
  12. Research on Dynamic Task Scheduling Strategy Based on Host Load Prediction,TP338
  13. Six degrees of freedom arm robot control study based on a neural network algorithm,TP242
  14. Differential Evolution Algorithm and Its Application in Clustering Analysis,O241
  15. Research on Several Key Routing Techniques for Wireless Sensor Networks,TP212.9
  16. Study on the Parallel Algorithms for Optimization Problems,O224
  17. Integrated Modeling and Optimization Design Technology of Structure and Control for Flexible Manipulator,TP241
  18. On High Performance Numerical Algorithm for Electromagnetic Scattering and EMC Analysis,TN974
  19. Research on the Development Planning and Evaluation of City Water Cycle System,TU991
  20. Study on Parallel FDTD Algorithm and Its Applications on PC and Blade Server Clusters,TN011
  21. Scheme Reserch and Optimal Assessment of Urban Power Grid Black-start,TM727.2

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