[Eecs_phd] EECS Research Seminar Talk with CS Interview Candidate Dr. Zhewei Wang - Advancing AI for Accuracy and Efficiency: Pushing the Boundaries of AI in Vision, NLP, and Edge Computing

• Previous message: [Eecs_phd] EECS Research Seminar Talk with CS Interview Candidate Dr. Ziyang Song-Deep and Probabilistic Representation Learning for Electronic Health Records
• Next message: [Eecs_phd] EECS Research Seminar Talk with CS Interview Candidate Dr. Niusen Chen-Safeguarding Data Confidentiality: From Deniable Encryption to Secure Deletion
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Title:  Advancing AI for Accuracy and Efficiency: Pushing the Boundaries of AI in Vision, NLP, and Edge Computing

Abstract:

Efforts to develop accurate and robust AI models span a wide range of tasks and applications, including medical image analysis (MedIA), natural language processing (NLP), and speech signal processing. In this talk, I will present my research in these areas, beginning with medical image analysis, where I introduce a semi-supervised learning approach for vessel segmentation in X-ray coronary angiography, and NLP, where I discuss a graph-based model for key information extraction, both designed to enhance accuracy in complex tasks. Next, I will highlight our efforts in developing low Size, Weight, and Power, Cost (SWaP-C) AI implementations using spiking neural networks (SNNs), specifically for speech enhancement, leveraging neuromorphic architectures for energy-efficient AI in edge computing. I will also discuss my ongoing collaborations with EECS faculty and outline my vision for future research and development.

Biography:

Zhewei Wang received his PhD and MS degrees in Computer Science from Ohio University in December 2020 and October 2019, respectively. He is currently a Visiting Assistant Professor in AI at the School of Electrical Engineering and Computer Science (EECS), Ohio University. Prior to this, he conducted research at Massachusetts General Hospital, Harvard Medical School (2021-2023), focusing on AI-driven medical image analysis. His research interests span Deep Learning, Machine Learning, Medical Image Analysis, Computer Vision, Natural Language Processing, and Reinforcement Learning. His work has been published in multiple conferences and journals, including ISBI, MLMI, and ICMLA.

________________________________________________________________________________
Microsoft Teams Need help?< https://aka.ms/JoinTeamsMeeting?omkt=en-US 
>
Join the meeting now< https://teams.microsoft.com/l/meetup-join/19%3ameeting_OThjYTdmYTktZjhlZi00YjNkLWI2OGUtZTdkNTMzMTQ5ZjBi%40thread.v2/0?context=%7b%22Tid%22%3a%22f3308007-477c-4a70-8889-34611817c55a%22%2c%22Oid%22%3a%22685c3f4f-29d5-4141-ada5-0fdeab8480e4%22%7d 
>
Meeting ID: 235 155 568 31
Passcode: NW7GK2vT
________________________________
Dial in by phone
+1 614-706-6572,,179859595#<tel:+16147066572,,179859595> United States, Columbus
Find a local number< https://dialin.teams.microsoft.com/8f5f7319-0053-4423-a154-4f8b6e7fb7dd?id=179859595 
>
Phone conference ID: 179 859 595#
For organizers: Meeting options< https://teams.microsoft.com/meetingOptions/?organizerId=685c3f4f-29d5-4141-ada5-0fdeab8480e4&tenantId=f3308007-477c-4a70-8889-34611817c55a&threadId=19_meeting_OThjYTdmYTktZjhlZi00YjNkLWI2OGUtZTdkNTMzMTQ5ZjBi@thread.v2&messageId=0&language=en-US 
> | Reset dial-in PIN< https://dialin.teams.microsoft.com/usp/pstnconferencing 
>
[ https://www.ohio.edu/sites/default/files/2018-11/invite_logo_teams.jpg 
]
If you encounter issues with this meeting, please visit the Help link. If you are not able to resolve the problems, please contact the meeting organizer to let them know you are having difficulty.
Org help< https://www.ohio.edu/oit/services/collaboration/teams/help 
>
________________________________________________________________________________

-------------- next part --------------
An HTML attachment was scrubbed...
URL: < http://listserv.ohio.edu/pipermail/eecs_phd/attachments/20250218/8dd6c1b6/attachment.html 
>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: text/calendar
Size: 10275 bytes
Desc: not available
URL: < http://listserv.ohio.edu/pipermail/eecs_phd/attachments/20250218/8dd6c1b6/attachment.ics 
>

• Previous message: [Eecs_phd] EECS Research Seminar Talk with CS Interview Candidate Dr. Ziyang Song-Deep and Probabilistic Representation Learning for Electronic Health Records
• Next message: [Eecs_phd] EECS Research Seminar Talk with CS Interview Candidate Dr. Niusen Chen-Safeguarding Data Confidentiality: From Deniable Encryption to Secure Deletion
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]