Machine Learning for Model Order Reduction

This Book discusses machine learning for model order reduction, which can be used in modern VLSI design to predict the behavior of an electronic circuit, via mathematical models that predict behavior. The author describes techniques to reduce significantly the time required for simulations involving large-scale ordinary differential equations, which sometimes take several days or even weeks. This method is called model order reduction (MOR), which reduces the complexity of the original large system and generates a reduced-order model (ROM) to represent the original one. Readers will gain in-depth knowledge of machine learning and model order reduction concepts, the tradeoffs involved with using various algorithms, and how to apply the techniques presented to circuit simulations and numerical analysis.



Introduces machine learning algorithms at the architecture level and the algorithm levels of abstraction;


Describes new, hybrid solutions for model order reduction;


Presents machine learning algorithms in depth, but simply;


Uses real, industrial applications to verify algorithms.

Aceasta carte discuta invatarea automata pentru reducerea comenzilor de model, care poate fi utilizata in proiectarea moderna VLSI pentru a prezice comportamentul unui circuit electronic, prin modele matematice care prezic comportamentul. Autorul descrie tehnici pentru a reduce semnificativ timpul necesar simularilor care implica ecuatii diferentiale obisnuite la scara larga, care uneori dureaza cateva zile sau chiar saptamani.