|
S
Sun
|
M
Mon
|
T
Tue
|
W
Wed
|
T
Thu
|
F
Fri
|
S
Sat
|
|---|---|---|---|---|---|---|
|
0 events,
|
1 event,
-
Please save the date to join us for this annual distinguished lecture. The Joseph Bordogna Forum will foster conversation and debate regarding important issues at the nexus of technology and society. It will feature lectures and panel discussions on a wide range of contemporary issues that are central to engineering including diversity and inclusion, the […] |
1 event,
-
Technologies that enable confidential communication and anonymous authentication are important for improving privacy for users of internet services. Unfortunately, encryption and anonymity, while good for privacy, make it hard to hold bad actors accountable for misbehavior. Internet services rely on seeing message content to detect spam and other harmful content; services must also be able […] |
1 event,
-
ABSTRACT: Electronic health records (EHRs) offer great promises in advancing clinical research and transforming learning health systems. However, complex, temporal EHRs are fraught with biases and present daunting analytical challenges that, if not addressed, can exacerbate health inequities. EHRs data, recorded at irregular time intervals with varying frequencies, are multi-modal and multi-scale including structured data […] |
1 event,
-
Algorithms make predictions about people constantly. The spread of such prediction systems has raised concerns that machine learning algorithms may exhibit problematic behavior, especially against individuals from marginalized groups. This talk will provide an overview of my research building a theory of "responsible" machine learning. I will highlight a notion of fairness in prediction, called […] |
0 events,
|
0 events,
|
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
|
0 events,
|
0 events,
|
1 event,
-
Scaling applications with distributed execution has become the norm. With the rise of big data and machine learning, more and more developers must build applications that involve complex and data-intensive distributed processing. In this talk, I will discuss the design of a general-purpose distributed execution system that can serve as a common platform for such […] |
1 event,
-
ABSTRACT: How can A.I.-based methods inform social listening applications during public health crises? The COVID-19 pandemic has uprooted the mode and method of human communication and interaction. The magnitude of the pandemic has led to an ‘infodemic’ along with considerable increase in stress and anxiety across communities. At the same time, the use of social […] |
1 event,
-
As networked systems become critical infrastructure, their design must reflect their new societal role. Today, we build systems with hundreds of heuristics but often do not understand their inherent and emergent behaviors. I will present a set of tools and techniques to prove performance properties of heuristics running in real-world conditions. Rigorous proofs can not […] |
0 events,
|
0 events,
|
|
0 events,
|
0 events,
|
1 event,
-
Building a state-of-the-art program optimizer, synthesizer, or verifier is still a gargantuan task for even programming language (PL) experts. Much of this challenge stems from the fact that term rewriting, a ubiquitous approach to manipulating programs, only works with one version of a program at a time. As a result, the system builder must carefully […] |
1 event,
-
ABSTRACT: Building robust decision making systems for autonomous systems is challenging. Decisions must be made based on imperfect information about the environment and with uncertainty about how the environment will evolve. In addition, these systems must carefully balance safety with other considerations, such as operational efficiency. Typically, the space of edge cases is vast, placing a large […] |
0 events,
|
0 events,
|
0 events,
|
|
0 events,
|
0 events,
|
2 events,
-
Pre-trained models have become a cornerstone of machine learning thanks to the fact that they can provide improved performance with less labeled data on downstream tasks. However, these models are typically created by resource-rich research groups that unilaterally decide how a given model should be built, trained, and released, after which point it is never […]
-
Please join Ruzena Bajcsy, Susan Davidson, Stephanie Weirich and Linh Phan for a panel discussion. Reception to Follow ABSTRACT: Women have always been part of computing at Penn, from the women who programmed the ENIAC, to the first woman faculty member, Ruzena Bajcsy, who arrived in 1972 as the CIS department was being formed, to […] |
1 event,
-
ABSTRACT: An important goal of the field sensorimotor robot learning is to do away with cumbersome expertise-intensive task specification, so that general-purpose robots of the future might learn large numbers of new skills. In this talk, I will discuss our recent work on algorithms that exploit goals as a versatile and accessible task specification interface. Goals might […] |
0 events,
|
0 events,
|
0 events,
|
