Machine learning augmented systems in medicine and music
Over the last 20 years, the field of artificial intelligence (AI) has experienced tremendous growth, with applications spanning a wide range of data rich fields of endeavor. At the core of many AI systems are machine learning algorithms that greatly improve system performance by leveraging patterns implicit in the data. In this talk I will showcase the use of neural sequence learning algorithms for simplifying or assisting human efforts in two different domains: medicine and music. On the medical side, I will describe a neural sequence-to-sequence semantic parsing model that is trained using reinforcement learning in order to automatically answer queries from doctors interested in understanding the state of a patient. I will then present ongoing work on a sequence learning approach for training music language models that can be used to generate variations on music originally created by human composers. Time permitting, I will conclude with an overview of the projects that are currently pursued in my group and jointly with my collaborators.
Razvan C. Bunescu is a Professor in the School of Electrical Engineering and Computer Science at Ohio University. He received the PhD degree in computer science from the University of Texas at Austin in 2007, with a thesis on machine learning methods for information extraction. His research interests lie in the general area of machine learning, with a focus on applications in natural language processing, music information retrieval, biomedical informatics, computer architecture, and more recently computational creativity. His work has been funded by grants from the National Science Foundation and the National Institutes of Health.
How to participate this via Webex :
Time: 11:00 AM - 12:20 PM Tuesday, Apr 28 2020 (UTC-04:00) Eastern Time (US & Canada)
Top of Form
Meeting number: 475 265 871
More ways to join
Join by video system
Dial [log in to unmask]
You can also dial 184.108.40.206 and enter your meeting number.
Join by phone
+1-415-655-0002 US Toll
+1-415-655-0002 US Toll
Access code: 475 265 871
From: Xiaojun Cao <[log in to unmask]>
Sent: Monday, April 27, 2020 2:54 PM
To: Tammie T Dudley <[log in to unmask]>; Yingshu Li <[log in to unmask]>
Subject: NextGen-AI research presentation by Dr. Razvan Bunescu (April 28, 11-12:30am)
This is the information of tomorrow’s talk.
Please share it with the graduate students.
Thanks a lot!
Xiaojun (Matt) Cao Ph.D.
Department of Computer Science
Georgia State University
Tel: (404) 413-5732, Fax: (404) 413-5717