Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Multilevel Optimization With Dropout For Neural Networks, Gary Joseph Saavedra
Multilevel Optimization With Dropout For Neural Networks, Gary Joseph Saavedra
Mathematics & Statistics ETDs
Large neural networks have become ubiquitous in machine learning. Despite their widespread use, the optimization process for training a neural network remains com-putationally expensive and does not necessarily create networks that generalize well to unseen data. In addition, the difficulty of training increases as the size of the neural network grows. In this thesis, we introduce the novel MGDrop and SMGDrop algorithms which use a multigrid optimization scheme with a dropout coarsening operator to train neural networks. In contrast to other standard neural network training schemes, MGDrop explicitly utilizes information from smaller sub-networks which act as approximations of the full …
Target Control Of Networked Systems, Isaac S. Klickstein
Target Control Of Networked Systems, Isaac S. Klickstein
Mechanical Engineering ETDs
The control of complex networks is an emerging field yet it has already garnered interest from across the scientific disciplines, from robotics to sociology. It has quickly been noticed that many of the classical techniques from controls engineering, while applicable, are not as illuminating as they were for single systems of relatively small dimension. Instead, properties borrowed from graph theory provide equivalent but more practical conditions to guarantee controllability, reachability, observability, and other typical properties of interest to the controls engineer when dealing with large networked systems. This manuscript covers three topics investigated in detail by the author: (i) the …
Electromagnetic Analysis Of Bidirectional Reflectance From Roughened Surfaces And Applications To Surface Shape Recovery, Julian Antolin Camarena
Electromagnetic Analysis Of Bidirectional Reflectance From Roughened Surfaces And Applications To Surface Shape Recovery, Julian Antolin Camarena
Physics & Astronomy ETDs
Scattering from randomly rough surfaces is a well-established sub area of electrodynamics. There remains much to be done since each surface and optical processes that may occur in within the scattering medium, and countless other scenarios, is different. There are also illumination models that describe lighting in a scene on the macroscopic scale where geometrical optics can be considered adequate. Of particular interest for us is the intersection of the physical scattering theories and the illumination models. We present two contributions: 1) A minimum of two independent images are needed since any opaque surface can be uniquely specified in terms …
Deterministic And Probabilistic Methods For Seismic Source Inversion, Juan Pablo Madrigal Cianci
Deterministic And Probabilistic Methods For Seismic Source Inversion, Juan Pablo Madrigal Cianci
Mathematics & Statistics ETDs
The national Earthquake Information Center (NEIC) reports an occurrence of about 13,000 earthquakes every year, spanning different values on the Richter scale from very mild (2) to "giant earthquakes'' (8 and above). Being able to study these earthquakes provides useful information for a wide range of applications in geophysics. In the present work we study the characteristics of an earthquake by performing seismic source inversion; a mathematical problem that, given some recorded data, produces a set of parameters that when used as input in a mathematical model for the earthquake generates synthetic data that closely resembles the measured data. There …