Liu, Chenchen
(2017)
Brain-Inspired Computing: Neuromorphic System Designs and Applications.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
This is the latest version of this item.
Abstract
In nowadays big data environment, the conventional computing platform based on von Neumann architecture encounters the bottleneck of the increasing requirement of computation capability and efficiency. The “brain-inspired computing” Neuromorphic Computing has demonstrated great potential to revolutionize the technology world. It is considered as one of the most promising solutions by achieving tremendous computing and power efficiency on a single chip. The neuromorphic computing systems represent great promise for many scientific and intelligent applications. Many designs have been proposed and realized with traditional CMOS technology, however, the progress is slow. Recently, the rebirth of neuromorphic computing is inspired by the development of novel nanotechnology.
In this thesis, I propose neuromorphic computing systems with the ReRAM (Memristor) crossbar array. It includes the work in three major parts: 1) Memristor devices modeling and related circuits design in resistive memory (ReRAM) technology by investigating their physical mechanism, statistical analysis, and intrinsic challenges. A weighted sensing scheme which assigns different weights to the cells on different bit lines was proposed. The area/power overhead of peripheral circuitry was effectively reduced while minimizing the amplitude of sneak paths. 2) Neuromorphic computing system designs by leveraging memristor devices and algorithm scaling in neural network and machine learning algorithms based on the similarity between memristive effect and biological synaptic behavior. First, a spiking neural network (SNN) with a rate coding model was developed in algorithm level and then mapped to hardware design for supervised learning. In addition, to further speed and accuracy improvement, another neuromorphic system adopting analog input signals with different voltage amplitude and a current sensing scheme was built. Moreover, the use of a single memristor crossbar for each neural net- work layer was explored. 3) The application-specific optimization for further reliability improvement of the developed neuromorphic systems. In this thesis, the impact of device failure on the memristor-based neuromorphic computing systems for cognitive applications was evaluated. Then, a retraining and a remapping design in algorithm level and hardware level were developed to rescue the large accuracy loss.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
26 September 2017 |
| Date Type: |
Publication |
| Defense Date: |
8 May 2017 |
| Approval Date: |
26 September 2017 |
| Submission Date: |
16 June 2017 |
| Access Restriction: |
1 year -- Restrict access to University of Pittsburgh for a period of 1 year. |
| Number of Pages: |
106 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Swanson School of Engineering > Electrical and Computer Engineering |
| Degree: |
PhD - Doctor of Philosophy |
| Thesis Type: |
Doctoral Dissertation |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
Memristor Crossbar, Neuromorphic Computing, Artificial Intelligence, Neural Network, Spiking, Current Sensing, Reliability |
| Date Deposited: |
26 Sep 2017 20:48 |
| Last Modified: |
26 Sep 2018 05:15 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/32549 |
Available Versions of this Item
-
Brain-Inspired Computing: Neuromorphic System Designs and Applications. (deposited 26 Sep 2017 20:48)
[Currently Displayed]
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}