Startseite Mathematik 3. Research of Blind Equalization Algorithms Based on FFNN
Kapitel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

3. Research of Blind Equalization Algorithms Based on FFNN

  • Liyi Zhang
Veröffentlichen auch Sie bei De Gruyter Brill
Erkunden Sie dieses Fachgebiet So veröffentlichen Sie bei uns
Blind Equalization in Neural Networks
Ein Kapitel aus dem Buch Blind Equalization in Neural Networks

Abstract

In this chapter, the basic principle of feed-forward neural network (FFNN) is analyzed. First, blind equalization algorithms based on the three-layer FFNN, fourlayer FFNN, and five-layer FFNN are studied. Then iteration formulas of algorithms are derived. Computer simulations are done. The theoretical analysis and experimental results verify that with the increase of layer number, the algorithm convergence rate becomes slow and the computational complexity increases. But the steady residual error decreases after the algorithm converged, that is, the approximation ability enhances. Second, the improved BP algorithm is applied to the blind equalization algorithm, then blind equalization algorithms based on the momentum term, time-varying momentum term, and variable step size are studied. When these new algorithms are compared with the blind equalization algorithm based on the traditional BP algorithm, the performances of the new algorithms can be improved.

Abstract

In this chapter, the basic principle of feed-forward neural network (FFNN) is analyzed. First, blind equalization algorithms based on the three-layer FFNN, fourlayer FFNN, and five-layer FFNN are studied. Then iteration formulas of algorithms are derived. Computer simulations are done. The theoretical analysis and experimental results verify that with the increase of layer number, the algorithm convergence rate becomes slow and the computational complexity increases. But the steady residual error decreases after the algorithm converged, that is, the approximation ability enhances. Second, the improved BP algorithm is applied to the blind equalization algorithm, then blind equalization algorithms based on the momentum term, time-varying momentum term, and variable step size are studied. When these new algorithms are compared with the blind equalization algorithm based on the traditional BP algorithm, the performances of the new algorithms can be improved.

Kapitel in diesem Buch

  1. Frontmatter I
  2. Preface V
  3. Contents VII
  4. 1. Introduction 1
  5. 2. The Fundamental Theory of Neural Network Blind Equalization Algorithm 17
  6. 3. Research of Blind Equalization Algorithms Based on FFNN 51
  7. 4. Research of Blind Equalization Algorithms Based on the FBNN 94
  8. 5. Research of Blind Equalization Algorithms Based on FNN 124
  9. 6. Blind Equalization Algorithm Based on Evolutionary Neural Network 149
  10. 7. Blind equalization Algorithm Based on Wavelet Neural Network 180
  11. 8. Application of Neural Network Blind Equalization Algorithm in Medical Image Processing 205
  12. Appendix A: Derivation of the Hidden Layer Weight Iterative Formula in the Blind Equalization Algorithm Based on the Complex Three-Layer FFNN 229
  13. Appendix B: Iterative Formulas Derivation of Complex Blind Equalization Algorithm Based on BRNN 231
  14. Appendix C: Types of Fuzzy Membership Function 235
  15. Appendix D: Iterative Formula Derivation of Blind Equalization Algorithm Based on DRFNN 239
  16. References 243
  17. Index 251
https://doi.org/10.1515/9783110450293-003

Kapitel in diesem Buch

  1. Frontmatter I
  2. Preface V
  3. Contents VII
  4. 1. Introduction 1
  5. 2. The Fundamental Theory of Neural Network Blind Equalization Algorithm 17
  6. 3. Research of Blind Equalization Algorithms Based on FFNN 51
  7. 4. Research of Blind Equalization Algorithms Based on the FBNN 94
  8. 5. Research of Blind Equalization Algorithms Based on FNN 124
  9. 6. Blind Equalization Algorithm Based on Evolutionary Neural Network 149
  10. 7. Blind equalization Algorithm Based on Wavelet Neural Network 180
  11. 8. Application of Neural Network Blind Equalization Algorithm in Medical Image Processing 205
  12. Appendix A: Derivation of the Hidden Layer Weight Iterative Formula in the Blind Equalization Algorithm Based on the Complex Three-Layer FFNN 229
  13. Appendix B: Iterative Formulas Derivation of Complex Blind Equalization Algorithm Based on BRNN 231
  14. Appendix C: Types of Fuzzy Membership Function 235
  15. Appendix D: Iterative Formula Derivation of Blind Equalization Algorithm Based on DRFNN 239
  16. References 243
  17. Index 251
Jetzt anmelden und 20% sparen
Institutioneller Zugang
Wie funktioniert Authentifizierung?
Haben Sie eine Idee, wie wir unsere Website verbessern können?
Bitte schreiben Sie uns.
© 2025 De Gruyter Brill
Heruntergeladen am 29.9.2025 von https://www.degruyterbrill.com/document/doi/10.1515/9783110450293-003/html
Button zum nach oben scrollen