Making Machine Learning Trustworthy in Vision Tasks

Speaker: Prof. Wenbo He
         McMaster University

Title:  "Making Machine Learning Trustworthy in Vision Tasks"

Date:   Monday, 22 April 2024

Time:   4:00pm - 5:00pm

Venue:  Lecture Theater F
        (Leung Yat Sing Lecture Theater), near lift 25/26


Recently, machine learning (ML) performance has drastically increased as a
result of powerful computing facilities and large datasets. However, the
inherent weaknesses in the reliability and security of data-centric
machine learning applications may result in performance degradation,
system misbehavior, and/or privacy breach. Building trustworthy
data-centric learning systems is among the biggest and most impactful
challenges in the next decade. In this talk I will briefly introduce
several of our recent research results addressing learning with noisy
labels and learning with privacy concerns. We seek to formulate the
trustworthy machine learning problems and design solutions to ensure the
robustness, trustworthiness, and privacy of data-centric machine learning


Wenbo He is currently an Associate Professor in the Department of
Computing and Software. Before joining McMaster, she was an Assistant
Professor in the School of Computer Science at McGill University from 2011
to 2016. She was an Assistant Professor in the Electrical Engineering
department at the University of Nebraska-Lincoln from 2010 to 2011, and an
Assistant Professor in the CS department at the University of New Mexico
from 2008 to 2010. She had 5-year industry experience (2000-2005) working
in Cisco Systems, Inc. in the US. She got the bachelor's and master's
Degree on Control Theory in 1995 and 1998 respectively. She got her Ph.D.
in 2008 from the Department of Computer Science at the University of
Illinois at Urbana-Champaign (UIUC). She received the Mavis Memorial Fund
Scholarship Award from the College of Engineering of UIUC in 2006 for
"excellent academic performance, research accomplishments, and
demonstrated leadership in engineering education", and the C. W. Gear
Outstanding Graduate Award in 2007 for "being one of the best graduate
students from the UIUC Department of Computer Science". Her papers won the
Best Paper Award from IEEE Transactions on Industrial Informatics in 2008,
and the Best Paper Award from ACM WiSec 2011. Her research focuses include
big data systems, AIoT systems, and trustworthy ML.