MS-EE-L Archives

April 2022

MS-EE-L@LISTSERV.GMU.EDU

Options: Use Proportional Font
Show HTML Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Jammie Chang <[log in to unmask]>
Reply To:
Jammie Chang <[log in to unmask]>
Date:
Thu, 21 Apr 2022 14:29:06 +0000
Content-Type:
multipart/alternative
Parts/Attachments:
text/plain (1703 bytes) , text/html (13 kB)
Dear All,

The following seminar unfortunately needed to be cancelled today. It will be rescheduled to next week. An updated announcement will be sent out soon.

Sorry for the inconvenience,
Jammie


Jammie Chang

Academic Program Manager

Department of Electrical and Computer Engineering

George Mason University

4400 University Drive, MSN 1G5

Fairfax, VA 22030

Phone: 703-993-1570

Fax: 703-993-1601



PhD ECE Seminar



Efficient Deep Learning System in Mobile Computing



By Zirui Xu

PhD Advisor: Dr. Xiang Chen



Thursday, April 21, 2022

1:00 PM – 2:00 PM

ENGR 3507



Participants are encouraged to complete Mason COVID Health✓™<https://www.gmu.edu/mason-covid-health-check> and receive a “green light” status on the day of the event.

Please send your RSVP request to [log in to unmask] with the info of seminar date, seminar title, your name.



Abstract



Although Deep Neural Networks (DNNs) have been widely applied in various cognitive applications, they are still very computationally intensive for resource-constrained mobile systems. In this talk, I will introduce my past research experience on optimizing DNN computing efficiency for mobile devices. First, I will introduce a neural design from the algorithm aspect, which shows better information extraction efficiency than the current neuron in DNNs; Second, I will explore the DNN inference optimization margin by showing computation redundancy from the input side; Third, we will focus on optimizing DNN models regarding specific resource constraints in mobile systems; At last, we show the system design of collaborative learning with massive mobile devices.

ATOM RSS1 RSS2