Date Approved
6-28-2024
Embargo Period
7-1-2024
Document Type
Thesis
Degree Name
Master of Science (M.S.)
Department
Electrical and Computer Engineering
College
Henry M. Rowan College of Engineering
Advisor
Ben Wu, Ph.D.
Committee Member 1
Huaxia Wang, Ph.D.
Committee Member 2
Guimu Guo, Ph.D.
Keywords
Analog; Blind Source Separation; Computing; Electronic; Neural Networks; Photonic
Subject(s)
Photonics; Computer systems
Disciplines
Computer Engineering | Electrical and Computer Engineering
Abstract
In the digital age, a wide variety of engineering problems have been solved, to a great deal of success, by digital computing techniques. The flexibility of software and relatively low cost of digital computing hardware make it an ideal starting point for solving a majority of tasks, and the numerical stability of software solutions make it highly appealing as the major workhorse for computational tasks. Despite this, many problems are actually suboptimally solved by digital methods, leading to systems with high latency, low throughput, power hungry parallel processing units and an excess of memory for discretizing sensor inputs. Computational photonic circuits are an emerging field of study which holds a number of advantages over modern digital computations. Their high bandwidth allows for the implementation of operations from basic arithmetic to frequency domain manipulation at speeds and efficiencies that their electrical counterparts are unable to approach, while still consuming less power per operation. This high bandwidth also enables parallelized computations in the same waveguide through the use of Wavelength-Division Multiplexing. Their analog nature allows for signal processing in continuous time, and eliminates the cost, memory requirements and precision loss resulting from the need to digitize massive amounts of data. This thesis will examine applications in which these circuits can provide a more optimal solution to tasks traditionally handled by software, and propose circuit architectures and control techniques that facilitate these more optimal solutions.
Recommended Citation
Garofolo, James Michael, "MATRIX PROCESSING WITH PHOTONIC ANALOG COMPUTING" (2024). Theses and Dissertations. 3267.
https://rdw.rowan.edu/etd/3267