## Applied Neural Networks for Signal ProcessingThe use of neural networks in signal processing is becoming increasingly widespread, with applications in many areas. Applied Neural Networks for Signal Processing is the first book to provide a comprehensive introduction to this broad field. It begins by covering the basic principles and models of neural networks in signal processing. The authors then discuss a number of powerful algorithms and architectures for a range of important problems, and describe practical implementation procedures. A key feature of the book is that many carefully designed simulation examples are included to help guide the reader in the development of systems for new applications. The book will be an invaluable reference for scientists and engineers working in communications, control or any other field related to signal processing. It can also be used as a textbook for graduate courses in electrical engineering and computer science. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

II | 1 |

III | 5 |

IV | 11 |

V | 16 |

VI | 20 |

VII | 22 |

VIII | 26 |

IX | 29 |

XLI | 188 |

XLII | 201 |

XLIII | 205 |

XLIV | 216 |

XLV | 217 |

XLVI | 223 |

XLVII | 229 |

XLVIII | 233 |

X | 32 |

XI | 33 |

XII | 45 |

XIII | 49 |

XIV | 51 |

XV | 58 |

XVI | 61 |

XVII | 63 |

XVIII | 65 |

XIX | 71 |

XX | 74 |

XXI | 80 |

XXII | 94 |

XXIII | 108 |

XXIV | 112 |

XXV | 117 |

XXVI | 121 |

XXVII | 122 |

XXIX | 126 |

XXX | 130 |

XXXI | 134 |

XXXII | 138 |

XXXIII | 150 |

XXXIV | 152 |

XXXV | 153 |

XXXVI | 162 |

XXXVII | 168 |

XXXVIII | 177 |

XXXIX | 181 |

XL | 185 |

### Other editions - View all

### Common terms and phrases

Acoustics activation function Adaptive autocorrelation beamformer blind equalization BP algorithm cellular neural network center vectors computational complexity Conf connection strength matrix connection weights convergence covariance matrix denote detector differential equations dynamic curves eigenvalue eigenvector eigenvector corresponding entropy error Gaussian hidden layer hidden neurons high-order neural network higher-order Hopfield neural network IEEE IEEE Int IEEE Trans initial input layer input vector iteration learning algorithm linear main-network MLP network network in Figure neural network approach noise subspace nonlinear equalizer nonlinear filters nonlinear mapping obtained optimization problem output layer output neuron output vector parameters performance Principal Component Proc RBF network real-time recurrent neural networks recursive respectively Section self-organizing sequence shown in Figure sigmoid function Signal Processing signal reconstruction smallest eigenvalue solution spectral estimation Speech and Signal stationary subnetwork sufficient statistic system identification target signal th neuron Theorem threshold unsupervised learning values vector X(n weight vector Wj(t zero

### Popular passages

Page 333 - Cowan, SA Billings, and PM Grant, "Parallel Recursive Prediction Error Algorithm for Training Layered Neural Networks.