Neural Networks for Optimization and Signal ProcessingA topical introduction on the ability of artificial neural networks to not only solve on-line a wide range of optimization problems but also to create new techniques and architectures. Provides in-depth coverage of mathematical modeling along with illustrative computer simulation results. |
Contents
Mathematical Preliminaries of Neurocomputing | 1 |
4 | 23 |
5 | 29 |
Copyright | |
12 other sections not shown
Common terms and phrases
adaptive analog applications approach approximation architecture associated assume basis block called Chapter circuit combinatorial optimization components connection consider constraints convergence corresponding cost defined derivative described determined differential equations discrete-time discussed dynamic eigenvalues eigenvectors employing energy function equality error estimation example formulated given gradient IEEE implementation input integrators iterative layer learning algorithm linear matrix means method minimize multipliers neural network neurons noise nonlinear norm Note obtained optimization problem orthogonal matrix output parameter penalty performance positive principal programming realization represents rule shown in Fig signals simple simulated solution solving standard symmetric symmetric matrix synaptic weights system of differential technique tion transformed units usually variables vector w₁ weights zero Σ Σ