Search
Now showing items 641-650 of 677
Vertical gallium nitride power devices on bulk native substrates
(Massachusetts Institute of Technology, 2017)
Lateral power devices based on AlGaN/GaN hetero-structures have achieved excellent performance in the medium power range applications. However for higher voltage higher current switches, a vertical structure is preferred ...
Automatic application-specific optimizations under FPGA memory abstractions
(Massachusetts Institute of Technology, 2017)
FPGA-based accelerators have great potential to achieve better performance and energy-efficiency compared to general-purpose solutions because FPGAs permit the tailoring of hardware to a particular application. This hardware ...
Deep learning and structured data
(Massachusetts Institute of Technology, 2018)
In the recent years deep learning has witnessed successful applications in many different domains such as visual object recognition, detection and segmentation, automatic speech recognition, natural language processing, ...
Magnetic logic circuits with high bit resolution for hardware acceleration
(Massachusetts Institute of Technology, 2017)
The ever-increasing demand for high-performance and low-power computing warrants an investigation of technologies beyond conventional digital transistor circuits. We explore a logic device based on magnetic domain walls, ...
Faster linear algebra for data analysis and machine learning
(Massachusetts Institute of Technology, 2018)
We study fast algorithms for linear algebraic problems that are ubiquitous in data analysis and machine learning. Examples include singular value decomposition and low-rank approximation, several varieties of linear ...
Active sensing in silicon-based MEMS resonators
(Massachusetts Institute of Technology, 2015)
Microelectromechanical resonators are advantageous over traditional LC tanks and o-chip quartz crystals due to their high quality factors, small size and low power consumption. FET-sensing has been demonstrated in resonant ...
Behavior-driven optimization techniques for scalable data exploration
(Massachusetts Institute of Technology, 2017)
Interactive visualizations are a popular medium used by scientists to explore, analyze and generally make sense of their data. However, with the overwhelming amounts of data that scientists collect from various instruments ...
Funnel libraries for real-time robust feedback motion planning
(Massachusetts Institute of Technology, 2016)
We consider the problem of generating motion plans for a robot that are guaranteed to succeed despite uncertainty in the environment, parametric model uncertainty, and disturbances. Furthermore, we consider scenarios where ...
Design and implementation of low-latency, low-power reconfigurable on-chip networks
(Massachusetts Institute of Technology, 2017)
In this dissertation, I tackle large, low-latency, low-power on-chip networks. I focus on two key challenges in the realization of such NoCs in practice: (1) the development of NoC design toolchains that can ease and ...
Quantum-mimetic imaging
(Massachusetts Institute of Technology, 2015)
Many recent experiments have explored the use of nonclassical states of light to perform imaging or sensing. Although these experiments require quantum descriptions of light to explain their behavior, the advantages they ...