News & EventsDepartment Events & Announcements
Events
-
Nov20
EVENT DETAILSmore info
less
Title: The Lifecycle of Data Science: A Framework for Advancing Computational and Data-enabled Research
Abstract
There is no crisis, but also no time for complacency” said the chair of the National Academies of Sciences, Engineering, and Medicine (NASEM) committee on "Reproducibility and Replicability in Science" in May 2019 (https://vimeo.com/335923468). Questions regarding reproducibility have arisen regarding the transparency of computational methods and discovery, in part due to the leveraging of data and compute resources for scientific and engineering advancements, now pervasive in a staggeringly broad range of academic disciplines and activities. In this talk I present the reproducibility definitions that emerged in our NASEM committee deliberations and discuss an abstract framework for conceptualizing and advancing data science as a discipline, called the Lifecycle of Data Science (forthcoming in CACM). This framework integrates the disparate components of data-enabled discovery, from hardware provisioning to applications to dissemination standards for verification and re-use to ethics, and thereby brings into contextual focus salient issues such as computational reproducibility, standards and policy, and curricular development. I then present the "Knowledge Integrator," an effort to conceptualize and enable the dissemination of reproducible research results based on the Lifecycle of Data Science and community engagement.
Bio
Victoria Stodden joined the School of Information Sciences as an associate professor in Fall 2014. She is a leading figure in the area of reproducibility in computational science, exploring how can we better ensure the reliability and usefulness of scientific results in the face of increasingly sophisticated computational approaches to research. Her work addresses a wide range of topics, including standards of openness for data and code sharing, legal and policy barriers to disseminating reproducible research, robustness in replicated findings, cyberinfrastructure to enable reproducibility, and scientific publishing practices. Stodden co-chairs the NSF Advisory Committee for CyberInfrastructure and is a member of the NSF Directorate for Computer and Information Science and Engineering (CISE) Advisory Committee. She also serves on the National Academies Committee on Responsible Science: Ensuring the Integrity of the Research Process.
Previously an assistant professor of statistics at Columbia University, Stodden taught courses in data science, reproducible research, and statistical theory and was affiliated with the Institute for Data Sciences and Engineering. She co-edited two books released in 2014—Privacy, Big Data, and the Public Good: Frameworks for Engagement published by Cambridge University Press and Implementing Reproducible Research published by Taylor & Francis. Stodden earned both her PhD in statistics and her law degree from Stanford University. She also holds a master’s degree in economics from the University of British Columbia and a bachelor’s degree in economics from the University of Ottawa.
TIME Wednesday, November 20, 2019 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Brianna White brianna.mello@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Sep29
EVENT DETAILS
lessLast day for tuition adjustment related to enrollment changes (to or from full-time) No reductions are made to bills for dropped or swapped classes after this date
TIME Tuesday, September 29, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Sep30
EVENT DETAILS
lessTitle:
Playing with Data: my path from a Math & CS undergrad to leading a Deep Learning team in quantitative finance, with many stops along the wayBiography
Nikolai Yakovenko is a research lead at Point72, a large hedge fund headquartered in Connecticut, specializing in deep learning for quantitative research. He first got into the field by training deep learning models to play competitive poker. Poker being a long standing interest, both as a (human) player, and coding up strategies for computer opponents. Since catching the deep learning bug, Nikolai has been an applied deep learning researcher at Twitter and Nvidia, where he developed deep learning models for problems ranging from personalized recommendations and conversational AI, to resume parsing and computational genomics, as well as dabbling in computer vision. Nikolai will walk through his journey from learning to code at an early age, undergrad and graduate school in math and computer science, joining the Google Search team, and various other projects before catching the deep learning wave five or six years ago.TIME Wednesday, September 30, 2020 at 5:00 PM - 6:00 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct1
EVENT DETAILS
lessIDEAL Theory of Deep Learning Special Quarter Seminar
Title: The Blind Men and the Elephant: The Mysteries of Deep Learning
Speaker: Babak Hassibi, Mose and Lillian S. Bohn Professor of Electrical Engineering and Computing and Mathematical Sciences, California Institute of Technology
Time: Thursday October 1, 2020, 11:30-12:30
Venue: See https://www.ideal.northwestern.edu/special-quarters/fall-2020/ for streaming link.
Abstract: Deep learning has demonstrably enjoyed a great deal of recent practical success and is arguably the main driver behind the resurgent interest in machine learning and AI. Despite its tremendous empirical achievements, we are far from a theoretical understanding of deep networks. In this talk, we will argue that the success of deep learning is not only due to the special deep architecture of the models, but also due to the behavior of the stochastic descent methods used, which play a key role in reaching "good" solutions that generalize well to unseen data. We will connect learning algorithms such as stochastic gradient descent (SGD) and stochastic mirror descent (SMD) to work in H-infinity control in the 1990's, and thereby explain the convergence and implicit-regularization behavior of the algorithms when we are highly over-parametrized (what is now being called the "interpolating regime"). This gives us insight into why deep networks exhibit such powerful generalization abilities, a phenomenon now being referred to as "the blessing of dimensionality".
Biography: Babak Hassibi was born in Tehran, Iran, in 1967. He received the B.S. in electrical engineering degree from the University of Tehran, Tehran, Iran, in 1989, and the M.S. and Ph.D. degrees in electrical engineering from Stanford University, Stanford, CA, USA, in 1993 and 1996, respectively. Since January 2001, he has been with the California Institute of Technology, where he is currently the Mose and Lilian S. Bohn Professor of electrical engineering. From 2008 to 2015, he was Executive Officer of electrical engineering, as well as Associate Director of information science and technology. From November 1998 to December 2000, he was a member of the Technical Staff with the Mathematical Sciences Research Center, Bell Laboratories, Murray Hill, NJ, USA. He has also held short-term appointments with the Ricoh California Research Center, the Indian Institute of Science, and Linkoping University, Sweden. His research interests include communications and information theory, control and network science, and signal processing and machine learning. He is the co-author of the books (both with A.H. Sayed and T. Kailath) Indefinite Quadratic Estimation and Control: A Unified Approach to $H^2$ and $H^\infty$ Theories (SIAM, 1999) and Linear Estimation (Prentice-Hall, 2000). He is a recipient of the Alborz Foundation Fellowship, 1999 O. Hugo Schuck Best Paper Award of the American Automatic Control Council (with H. Hindi and S. P. Boyd), 2002 National Science Foundation Career Award, 2002 Okawa Foundation Research Grant for Information and Telecommunications, 2003 David and Lucille Packard Fellowship for Science and Engineering, 2003 Presidential Early Career Award for Scientists and Engineers (PECASE), and 2009 Al-Marai Award for Innovative Research in Communications, and was a participant in the 2004 National Academy of Engineering “Frontiers in Engineering” program.
TIME Thursday, October 1, 2020 at 11:30 AM - 12:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct5
EVENT DETAILS
lessLive Stream link:
https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=622cd1a9-eccb-40d4-8f7c-ac42013ca002Title:
How to reason about typical instances of algorithmic problemsAbstract
Worst-case analysis has traditionally been the tool of choice to measure the performance of algorithms and has led to a rich theory of algorithms and computational complexity. However, for many computational problems there is a large disconnect between our theoretical and practical understanding of their complexity. Many fundamental problems in machine learning and data analysis like clustering and inference correspond to well-studied algorithmic problems that are NP-hard in the worst-case, yet heuristics seem effective in solving ``typical'' instances of these theoretically hard problems. On the other extreme, statistical models of data are ubiquitous in machine learning. However, real-world instances are often noisy. Yet many algorithms for these models are often not robust – they are tailored to the specific distribution or model, and brittle to small amounts of modeling errors. This leads to the following major challenge.Can we develop new theoretical frameworks that address the disconnect between theory and practice, by reasoning about ``typical'' instances of problems?
Towards addressing this challenge, we will consider paradigms like smoothed analysis and semi-random models that go beyond traditional worst-case analysis to reason about typical instances of algorithmic problems. I will use these paradigms to design efficient algorithms with strong guarantees for NP-hard problems like clustering, learning probabilistic models, tensor decompositions, high-dimensional inference etc. We will also see how these approaches can help in designing robust and reliable algorithms for machine learning that are reliable in the presence of errors and adversarial corruptions.
Biography
Aravindan Vijayaraghavan is an Assistant Professor of Computer Science at Northwestern University. He obtained his PhD in Computer Science from Princeton University in 2012, followed by postdoctoral fellowships at Carnegie Mellon University (as the Simons postdoctoral fellow), and the Courant Institute (with the Simons Collaboration on Algorithms & Geometry). His research interests are in designing efficient algorithms for problems in machine learning and combinatorial optimization, and in using paradigms that go beyond worst-case analysis to obtain good algorithmic guarantees. He is a recipient of the NSF CAREER award and is a co-director of the NSF-funded Institute for Data, Econometrics, Algorithms and Learning (IDEAL).TIME Monday, October 5, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct9
EVENT DETAILS
lessLive Stream link:
TBATitle:
TBAAbstract
TBABiography
TBATIME Friday, October 9, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct12
EVENT DETAILS
lessTitle:
Exploring the Tradeoffs Between Performance and Power for Parallel, Scientific ApplicationsAbstract
The demand for computational power continues to drive the deployment of ever-growing parallel systems. Production parallel systems with hundreds of thousands of components are being designed and deployed. Future parallel systems are expected to have millions of processors and hundreds of millions of cores, with significant power requirements. The complexity of these systems is increasing, with hierarchically configured manycore processors and accelerators, together with a deep and complex memory hierarchy. As a result of the complexity, applications face a significant challenge in exploiting the necessary parameters for efficient execution. While reducing execution time is still the major objective for high performance computing, future systems and applications will have additional power requirements that represent a multidimensional tuning challenge. To embrace these key challenges, we must understand the complicated tradeoffs among runtime and power. This talk will present our methods and analyses to explore these tradeoffs for parallel, scientific applications.Biography
Valerie Taylor is the Director of the Mathematics and Computer Science Division and Argonne Distinguished Fellow at Argonne National Laboratory. Prior to joining Argonne, she was the Senior Associate Dean of Academic Affairs in the College of Engineering and a Regents Professor and the Royce E. Wisenbaker Professor in the Department of Computer Science and Engineering at Texas A&M University. In 2003, she joined Texas A&M University as the Department Head of CSE, where she remained in that position until 2011. Prior to joining Texas A&M, Valerie Taylor was a member of the faculty in the EECS Department at Northwestern University for eleven years. Her research is in the area of high-performance computing, with a focus on performance analysis and modeling of parallel, scientific applications. She is also the Executive Director of the Center for Minorities and People with Disabilities in IT (CMD-IT). Valerie Taylor is an IEEE Fellow and an ACM Fellow.TIME Monday, October 12, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct13
EVENT DETAILS
lessTitle:
TBAAbstract
TBABiography
TBATIME Tuesday, October 13, 2020 at 5:00 PM - 6:00 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct15
EVENT DETAILS
lessUndergraduate petition to graduate due for Winter 2021 graduation
TIME Thursday, October 15, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Oct19
EVENT DETAILS
lessLive Stream link:
TBATitle:
TBAAbstract
TBABiography
TBATIME Monday, October 19, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct19
EVENT DETAILS
lessTitle:
TBAAbstract
TBABiography
TBATIME Monday, October 19, 2020 at 5:00 PM - 6:00 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct21
EVENT DETAILS
lessLive Stream link:
TBATitle:
TBAAbstract
TBABiography
TBATIME Wednesday, October 21, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct26
EVENT DETAILS
lessLive Stream link:
TBATitle:
TBAAbstract
TBABiography
TBATIME Monday, October 26, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Oct28
EVENT DETAILS
lessLive Stream link:
TBATitle:
New Approaches for Characterizing Perception using Human-Computer Interfaces: Implications for StrokeAbstract
Activities of daily living require not only the correct generation of movements, but also the accurate interpretation of those movements. Mundane tasks, such as cutting an apple and pulling open a drawer, can be challenging and potentially dangerous when one’s perception of their movements is compromised. Additionally, accurate perception is an indispensable part of motor learning as it facilitates the acquisition of new skills, such as when training one’s tennis game. In the USA, 6.6 million adults, or 2-3% of the population, report living with a physical disability due to stroke. While the main focus of research on stroke and physical disability has been on changes occurring in the generation of movements, very little attention has been given to how these generated movements are perceived. Research that has been conducted suggests that 5.6 million individuals who survive a stroke are facing difficulty accurately perceiving their actions due to the damage at their brain. Given that we rely on the perception at our limbs to learn and become adept in controlling our movements, value exists in understanding the processes contributing to intact and inaccurate perception. Furthermore, by understanding the reason that inaccurate perception occurs, we can develop science-based interventions that lead to improved sensorimotor outcomes in millions of stroke survivors.
In this seminar, I will discuss our interdisciplinary approach for improving the understanding of how humans perceive their actions. I will review the novel assessment protocols that my lab created based on human-computer interfaces of our own design. For one approach, we use an instrumented device and automated audiovisual feedback to guide participants in activating numerous joints within a single arm. This approach has opened up innovative ways to address questions that have never before been studied. For example, we can determine the impact of activation of one joint on perception at a second joint, which is relevant to understanding how humans perceive during multi-joint tasks. Furthermore, we can understand the role of non-volitional actions, which arise from a change in brain circuitry, on perception in individuals post stroke. This is important for considering how to accurately assess and treat perceptual deficits in the stroke population. I will share our discoveries indicating when individuals post stroke may inaccurately perceive their actions. Additionally, I will provide an overview of our latest work in which we are using human-computer interfaces to create a rehabilitation intervention. Moreover, I will present our current efforts in employing machine-learning methods to address how signals arising from the brain may create the percept. The clinical relevance of this work includes underscoring the importance of accurate perception, developing appropriate perceptual assessment methods, and providing a rehabilitation treatment.
Biography
Dr. Netta Gurari is an Assistant Professor in the Department of Physical Therapy and Human Movement Sciences at Northwestern University. Additionally, Dr. Gurari holds a courtesy appointment with the Department of Mechanical Engineering and is a faculty affiliate of the Master of Science in Robotics Program at Northwestern University. She directs the Robotics and Sensorimotor Control Lab, which is comprised of a multi-disciplinary research team that is investigating how humans perceive somatosensory signals of their upper limbs. This research is executed through behavioral studies and is achieved by integrating tools and knowledge from areas including robotics, cognitive neuroscience, electrophysiology, neuroimaging, and physical therapy. Dr. Gurari received her B.S.E. from the University of Pennsylvania and M.S.E. and Ph.D. from Johns Hopkins University, all in Mechanical Engineering. Dr. Gurari is the recipient of numerous grants, including most recently an NIH K25 Career Development Award.TIME Wednesday, October 28, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Nov2
EVENT DETAILS
lessPre-registration for Winter Quarter begins
This is the original date for winter registration – will be re-scheduled for later in fall quarter.
TIME Monday, November 2, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Nov4
EVENT DETAILS
lessLive Stream link:
TBATitle:
TBAAbstract
TBABiography
TBATIME Wednesday, November 4, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Nov6
EVENT DETAILS
lessLast day to drop a class for Fall. (No tuition adjustment after September 29)
TIME Friday, November 6, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Nov9
EVENT DETAILS
lessRegistration for Winter 2021 begins
This is the original date for winter registration – will be re-scheduled for later in fall quarter.
TIME Monday, November 9, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Nov9
EVENT DETAILS
lessTitle:
TBAAbstract
TBABiography
TBATIME Monday, November 9, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Nov11
EVENT DETAILS
lessTitle:
TBAAbstract
TBABiography
TBATIME Wednesday, November 11, 2020 at 5:00 PM - 6:00 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Nov16
EVENT DETAILS
lessLive Stream link:
TBATitle:
TBAAbstract
TBABiography
TBATIME Monday, November 16, 2020 at 12:30 PM - 1:30 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Nov18
EVENT DETAILS
lessTitle:
TBAAbstract
TBABiography
TBATIME Wednesday, November 18, 2020 at 5:00 PM - 6:00 PM
CONTACT Pam Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Nov24
EVENT DETAILS
lessFall classes end
TIME Tuesday, November 24, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Nov25
EVENT DETAILS
lessThanksgiving vacation begins 6 p.m.
TIME Wednesday, November 25, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar