Print Email Facebook Twitter Tuning of Optical Beamforming Networks: A Deep Learning Approach Title Tuning of Optical Beamforming Networks: A Deep Learning Approach Author Nugroho, H. Contributor Wahls, S. (mentor) Bliek, L. (mentor) Verhaegen, M. (mentor) Faculty Mechanical, Maritime and Materials Engineering Department Delft Center for Systems and Control Programme Systems and Control Date 2015-10-28 Abstract Optical beamforming networks (OBFNs), which consist of many small and flat antennas, called phased array antennas (PAAs), can be tuned such that the signal beam from the airplanes can be steered towards a satellite. This was proposed as a alternative to the mechanically steered antenna, which has many disadvantages. The problem of tuning a large-scale OBFN is in many aspects similar to training a deep neural network. The tuning methodology developed in this thesis is based on the feedback that can be measured in real system. The deep learning approach is data driven, which tunes OBFNs from a given set of training examples. This is essential for online tuning in the future research. The deep learning approach is proven to work well for tuning large-scale OBFNs, e.g., 8x1, 16x1, and 32x1 binary tree structured OBFNs for any desired delays. Subject deep learningneural networkmachine learningoptical beamforming networksnon-linear optimizationthesisMSccontroldata drivenauto-encodersdropout regularizationsoverfittingfrequency overfitting To reference this document use: http://resolver.tudelft.nl/uuid:58764aa2-6894-44c5-89dd-4679f993923c Part of collection Student theses Document type master thesis Rights (c) 2015 Herminarto Nugroho, H. Files PDF Herminarto_Nugroho_430913 ... proach.pdf 6.26 MB Close viewer /islandora/object/uuid:58764aa2-6894-44c5-89dd-4679f993923c/datastream/OBJ/view