Colloquium Details
Insights from Deep Representations for Machine Learning Systems and Human Collaborations
Speaker: Maithra Raghu, Cornell University
Location: 60 Fifth Avenue room 150
Date: March 6, 2020, 11 a.m.
Host: Michael Overton
Synopsis:
The fundamental breakthroughs in machine learning, and the
rapid advancements of the underlying deep neural network models have
enabled the potential use of these systems in specialized, high stakes
domains such as healthcare. However, despite this remarkable progress,
the design of machine learning systems remains laborious,
computationally expensive and opaque, sometimes resulting in
catastrophic failures and significantly hindering their ability to work
with human experts, who play critical roles in these settings. In this
talk, I overview steps towards an insight-driven design of machine
learning systems, and methods to facilitate collaboration with human
experts. I develop tools that enable the quantitative analysis of the
complex hidden layers of deep neural networks, which provide both
fundamental insights on central components of the models as well as
informing algorithms for efficiently training these systems. I
demonstrate how these trained systems can be adapted to work effectively
with human experts, resulting in better outcomes than either entity alone.
Speaker Bio:
Maithra Raghu is a computer science PhD Candidate at Cornell
University advised by Jon Kleinberg and a research associate at Google
Brain. Her work centers on developing quantitative tools to gain
insights into deep neural network representations, and using these
insights to inform better design and training of ML systems, as well as
investigations on how these systems can work with human experts in
specialized domains such as medicine and healthcare. Her work has been
featured in many press outlets including The Washington Post, WIRED and
Quanta Magazine. She has been named one of the Forbes 30 Under 30 in
Science and a Rising Star in EECS. Prior to her PhD, Maithra received
her BA and Masters in Mathematics with First Class Honors at the
University of Cambridge.
Notes:
In-person attendance only available to those with active NYU ID cards.