Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Thesis_PhD_Raqib revised final format approved LW 4-1-16.pdf (2.05 MB)
ETD Abstract Container
Abstract Header
Memristor Based Low Power High Throughput Circuits and Systems Design
Author Info
Hasan, Md Raqibul
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1459522347
Abstract Details
Year and Degree
2016, Doctor of Philosophy (Ph.D.), University of Dayton, Electrical Engineering.
Abstract
Power density constraint and device reliability issues are driving energy efficient, fault tolerant architecture designs in recent years. With the emergence of big data applications low power, high throughput architectures are getting more interest. Neural networks have diverse use in the areas including big data analysis, sensor and signal processing applications. The memristor is a novel device having a large varying resistance range. Physical memristors can be laid out in a high density grid known as a crossbar. A memristor crossbar can evaluate many multiply-add operations in parallel in analog domain which is the dominant operation in neural network applications. The objective of this thesis is to examine memristor based extreme low power neuromorphic architectures for signal and big data processing applications. This thesis examines in-situ training of memristor based multi-layer neural networks where the entire crossbar is updated in four steps for a training instance (data). Existing training approaches update a crossbar serially column by column. Training of memristor based deep neural networks are examined using autoencoders for layer-wise pre-training of the networks. We propose a novel technique for ex-situ training of memristor based neural networks which takes sneak-path currents into consideration. Multicore architectures based on memristor neural cores are developed and system level area power are compared with traditional computing systems. Results show that the memristor neural network based architectures could be about five orders of magnitude more energy efficient when compared to the traditional computing systems.
Committee
Tarek Taha, Ph.D. (Committee Chair)
Vijayan Asari, Ph.D. (Committee Member)
John Loomis, Ph.D. (Committee Member)
Zhongmei Yao, Ph.D. (Committee Member)
Pages
190 p.
Subject Headings
Computer Engineering
;
Electrical Engineering
Keywords
Memristor crossbar
;
neural networks
;
training
;
multicore architecture, low power system
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Hasan, M. R. (2016).
Memristor Based Low Power High Throughput Circuits and Systems Design
[Doctoral dissertation, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1459522347
APA Style (7th edition)
Hasan, Md Raqibul.
Memristor Based Low Power High Throughput Circuits and Systems Design.
2016. University of Dayton, Doctoral dissertation.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1459522347.
MLA Style (8th edition)
Hasan, Md Raqibul. "Memristor Based Low Power High Throughput Circuits and Systems Design." Doctoral dissertation, University of Dayton, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1459522347
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
dayton1459522347
Download Count:
3,498
Copyright Info
© 2016, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.