Adjoint Neural Network Methods for Linear and Nonlinear Applications
Microwave electronic-photonic component modelling
Versandkostenfrei!
Versandfertig in 6-10 Tagen
47,99 €
inkl. MwSt.
PAYBACK Punkte
24 °P sammeln!
Artificial neural networks have recently emerged as a powerful tool for modelling devices. The objective of this book is to develop sensitivity based neural network techniques for both frequency domain and transient modelling of circuits. The first contribution is the development of SAANN technique for modelling microwave passive components which adds sensitivity data to the obtained model while reducing the amount of training data required for model development increasing the efficiency of process. As a further contribution, this book presents a novel technique, ASSDNN, for transient modellin...
Artificial neural networks have recently emerged as a powerful tool for modelling devices. The objective of this book is to develop sensitivity based neural network techniques for both frequency domain and transient modelling of circuits. The first contribution is the development of SAANN technique for modelling microwave passive components which adds sensitivity data to the obtained model while reducing the amount of training data required for model development increasing the efficiency of process. As a further contribution, this book presents a novel technique, ASSDNN, for transient modelling of optical/electrical components. This technique adds time-domain sensitivity data, which does not exist in current optoelectronic simulators, to the output of the obtained model while requiring less training data for model creation and consequently makes training more efficient. Furthermore, this technique was developed such that it can take advantage of parallel computation. This resultsin the technique being more efficient than conventional transient modelling techniques. In addition, the evaluation time for models generated using this technique is smaller compared to current simulators.
Andere Kunden interessierten sich für
