Happening @ Michigan https://events.umich.edu/list/rss RSS Feed for Happening @ Michigan Events at the University of Michigan. A Data Scientist Plays Games (April 3, 2020 3:00pm) https://events.umich.edu/event/74087 74087-18518838@events.umich.edu Event Begins: Friday, April 3, 2020 3:00pm
Location:
Organized By: Michigan Institute for Data Science

This event will be hosted online via Zoom

A Data Scientist Plays Games:  This is a presentation broken down into two parts.  The first is how to use mathematical techniques to analyze classic card and board games, and the second part is how data science techniques were applied in real life to support games on the Facebook platform.  This presentation is about 1.5 hours, with a target audience probably suited to CS/software engineering.  It’s light-hearted and fun.

Nick Berry, a native of the UK, has lived in Seattle for the last 25 years. He was educated as a rocket scientist and aircraft designer, graduating with a Masters Degree in Aeronautical and Astronautical Engineering.

Upon graduation, he joined a group of friends to form a software company, specializing in electronic mapping and route planning. This company was grown organically, and earned an unprecedented number of awards and accolades, including the British Design Award and The Queen’s Award for Technology, presented by Her Majesty in 1991. In 1994 Nick was recognized by the Sunday Times Magazine as “One of the top 50 entrepreneurs of the decade”. In 1994, after the company had grown to 50 people worldwide, it was sold to Microsoft.

Nick moved to America with the sale and spent 14 years working for Microsoft, the last ten of which were in the Microsoft Casual Game team. During his tenure, he filed a variety of patents for Microsoft, and represented Microsoft at various conferences and speaking engagements.

After leaving Microsoft, he joined RealNetworks to work as the GM of customer analytics for their games division, GameHouse.

After GameHouse, Nick spent five years as a Data Scientist, working for Facebook in their Seattle office.

In addition to his engineering expertise, Nick is passionate about data privacy and holds a CIPP qualification from the International Association of Privacy Professionals. He is an active member of the privacy community and speaks at various events about the legal and ethical aspects of data collection, use, and destruction.

In July 2013, Nick gave a TEDx talk about Passwords and the Internet, and in 2015 was nominated by GeekWire as Geek-of-the-week. In 2019 he was recognized as one of the 50 over 50 in the video games industry.

]]>
Workshop / Seminar Mon, 06 Apr 2020 11:11:49 -0400 2020-04-03T15:00:00-04:00 2020-04-03T16:00:00-04:00 Michigan Institute for Data Science Workshop / Seminar Nick Berry
A Data Scientist Plays Games (April 3, 2020 3:00pm) https://events.umich.edu/event/74087 74087-18518837@events.umich.edu Event Begins: Friday, April 3, 2020 3:00pm
Location:
Organized By: Michigan Institute for Data Science

This event will be hosted online via Zoom

A Data Scientist Plays Games:  This is a presentation broken down into two parts.  The first is how to use mathematical techniques to analyze classic card and board games, and the second part is how data science techniques were applied in real life to support games on the Facebook platform.  This presentation is about 1.5 hours, with a target audience probably suited to CS/software engineering.  It’s light-hearted and fun.

Nick Berry, a native of the UK, has lived in Seattle for the last 25 years. He was educated as a rocket scientist and aircraft designer, graduating with a Masters Degree in Aeronautical and Astronautical Engineering.

Upon graduation, he joined a group of friends to form a software company, specializing in electronic mapping and route planning. This company was grown organically, and earned an unprecedented number of awards and accolades, including the British Design Award and The Queen’s Award for Technology, presented by Her Majesty in 1991. In 1994 Nick was recognized by the Sunday Times Magazine as “One of the top 50 entrepreneurs of the decade”. In 1994, after the company had grown to 50 people worldwide, it was sold to Microsoft.

Nick moved to America with the sale and spent 14 years working for Microsoft, the last ten of which were in the Microsoft Casual Game team. During his tenure, he filed a variety of patents for Microsoft, and represented Microsoft at various conferences and speaking engagements.

After leaving Microsoft, he joined RealNetworks to work as the GM of customer analytics for their games division, GameHouse.

After GameHouse, Nick spent five years as a Data Scientist, working for Facebook in their Seattle office.

In addition to his engineering expertise, Nick is passionate about data privacy and holds a CIPP qualification from the International Association of Privacy Professionals. He is an active member of the privacy community and speaks at various events about the legal and ethical aspects of data collection, use, and destruction.

In July 2013, Nick gave a TEDx talk about Passwords and the Internet, and in 2015 was nominated by GeekWire as Geek-of-the-week. In 2019 he was recognized as one of the 50 over 50 in the video games industry.

]]>
Workshop / Seminar Mon, 06 Apr 2020 11:11:49 -0400 2020-04-03T15:00:00-04:00 2020-04-03T16:00:00-04:00 Michigan Institute for Data Science Workshop / Seminar Nick Berry
A Data Scientist Plays Games (April 3, 2020 3:00pm) https://events.umich.edu/event/74087 74087-18518836@events.umich.edu Event Begins: Friday, April 3, 2020 3:00pm
Location:
Organized By: Michigan Institute for Data Science

This event will be hosted online via Zoom

A Data Scientist Plays Games:  This is a presentation broken down into two parts.  The first is how to use mathematical techniques to analyze classic card and board games, and the second part is how data science techniques were applied in real life to support games on the Facebook platform.  This presentation is about 1.5 hours, with a target audience probably suited to CS/software engineering.  It’s light-hearted and fun.

Nick Berry, a native of the UK, has lived in Seattle for the last 25 years. He was educated as a rocket scientist and aircraft designer, graduating with a Masters Degree in Aeronautical and Astronautical Engineering.

Upon graduation, he joined a group of friends to form a software company, specializing in electronic mapping and route planning. This company was grown organically, and earned an unprecedented number of awards and accolades, including the British Design Award and The Queen’s Award for Technology, presented by Her Majesty in 1991. In 1994 Nick was recognized by the Sunday Times Magazine as “One of the top 50 entrepreneurs of the decade”. In 1994, after the company had grown to 50 people worldwide, it was sold to Microsoft.

Nick moved to America with the sale and spent 14 years working for Microsoft, the last ten of which were in the Microsoft Casual Game team. During his tenure, he filed a variety of patents for Microsoft, and represented Microsoft at various conferences and speaking engagements.

After leaving Microsoft, he joined RealNetworks to work as the GM of customer analytics for their games division, GameHouse.

After GameHouse, Nick spent five years as a Data Scientist, working for Facebook in their Seattle office.

In addition to his engineering expertise, Nick is passionate about data privacy and holds a CIPP qualification from the International Association of Privacy Professionals. He is an active member of the privacy community and speaks at various events about the legal and ethical aspects of data collection, use, and destruction.

In July 2013, Nick gave a TEDx talk about Passwords and the Internet, and in 2015 was nominated by GeekWire as Geek-of-the-week. In 2019 he was recognized as one of the 50 over 50 in the video games industry.

]]>
Workshop / Seminar Mon, 06 Apr 2020 11:11:49 -0400 2020-04-03T15:00:00-04:00 2020-04-03T16:00:00-04:00 Michigan Institute for Data Science Workshop / Seminar Nick Berry
Webinar: 2020 MICDE Catalyst Grants Showcase (April 9, 2020 10:00am) https://events.umich.edu/event/72740 72740-18070544@events.umich.edu Event Begins: Thursday, April 9, 2020 10:00am
Location:
Organized By: Michigan Institute for Computational Discovery and Engineering

This webinar will showcase some of the game-changing research supported by our Catalyst Grants program.

Session I Speakers:

Robert Krasny (Mathematics), "Integral equation based methods for scientific computing";

Vikram Gavini (Mechanical Engineering), "Long time-scale simulations using exponential time propagators";

and Yulin Pan (Naval Architecture and Marine Engineering), "Real-time phase-resolved ocean wave forecast with data assimilation enabled by GPU-accelerated computation".


Join the Webinar (via BlueJeans Events)

]]>
Livestream / Virtual Wed, 08 Apr 2020 09:43:05 -0400 2020-04-09T10:00:00-04:00 2020-04-09T11:30:00-04:00 Michigan Institute for Computational Discovery and Engineering Livestream / Virtual MICDE
A Data Scientist Plays Games (April 16, 2020 12:00pm) https://events.umich.edu/event/74087 74087-18510444@events.umich.edu Event Begins: Thursday, April 16, 2020 12:00pm
Location:
Organized By: Michigan Institute for Data Science

This event will be hosted online via Zoom

A Data Scientist Plays Games:  This is a presentation broken down into two parts.  The first is how to use mathematical techniques to analyze classic card and board games, and the second part is how data science techniques were applied in real life to support games on the Facebook platform.  This presentation is about 1.5 hours, with a target audience probably suited to CS/software engineering.  It’s light-hearted and fun.

Nick Berry, a native of the UK, has lived in Seattle for the last 25 years. He was educated as a rocket scientist and aircraft designer, graduating with a Masters Degree in Aeronautical and Astronautical Engineering.

Upon graduation, he joined a group of friends to form a software company, specializing in electronic mapping and route planning. This company was grown organically, and earned an unprecedented number of awards and accolades, including the British Design Award and The Queen’s Award for Technology, presented by Her Majesty in 1991. In 1994 Nick was recognized by the Sunday Times Magazine as “One of the top 50 entrepreneurs of the decade”. In 1994, after the company had grown to 50 people worldwide, it was sold to Microsoft.

Nick moved to America with the sale and spent 14 years working for Microsoft, the last ten of which were in the Microsoft Casual Game team. During his tenure, he filed a variety of patents for Microsoft, and represented Microsoft at various conferences and speaking engagements.

After leaving Microsoft, he joined RealNetworks to work as the GM of customer analytics for their games division, GameHouse.

After GameHouse, Nick spent five years as a Data Scientist, working for Facebook in their Seattle office.

In addition to his engineering expertise, Nick is passionate about data privacy and holds a CIPP qualification from the International Association of Privacy Professionals. He is an active member of the privacy community and speaks at various events about the legal and ethical aspects of data collection, use, and destruction.

In July 2013, Nick gave a TEDx talk about Passwords and the Internet, and in 2015 was nominated by GeekWire as Geek-of-the-week. In 2019 he was recognized as one of the 50 over 50 in the video games industry.

]]>
Workshop / Seminar Mon, 06 Apr 2020 11:11:49 -0400 2020-04-16T12:00:00-04:00 2020-04-16T13:30:00-04:00 Michigan Institute for Data Science Workshop / Seminar Nick Berry
Juneteenth Celebration (June 19, 2020 1:00pm) https://events.umich.edu/event/74968 74968-19112548@events.umich.edu Event Begins: Friday, June 19, 2020 1:00pm
Location: Off Campus Location
Organized By: Electrical and Computer Engineering

EECS invites you to our first Juneteenth celebration this Friday from 1:00pm – 2:00pm EDT!

Juneteenth is the oldest nationally celebrated commemoration of the ending of slavery in the United States. It celebrates African American freedom and achievement. Its goal is to promote and cultivate knowledge and appreciation of African American history and culture while encouraging continuous self-development and respect for all cultures.

Our Juneteenth celebration will include:
Performance of the Black National Anthem
Reading of the Emancipation Proclamation
Students will share their stories and experiences
Presentation of a student proposal on how to improve the culture for Black students in EECS to the department Chairs

All are welcome to attend!

]]>
Livestream / Virtual Tue, 16 Jun 2020 14:29:17 -0400 2020-06-19T13:00:00-04:00 2020-06-19T14:00:00-04:00 Off Campus Location Electrical and Computer Engineering Livestream / Virtual Juneteenth graphic
Hands-on Workshop: Creating a Hybrid Simulation System Using the Simple Run Time Infrastructure Software (October 9, 2020 4:00pm) https://events.umich.edu/event/76684 76684-19735053@events.umich.edu Event Begins: Friday, October 9, 2020 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Computational Discovery and Engineering

The goal of this hands-on workshop is to introduce the Simple Run-Time Infrastructure software toolkit (SRTI) to the participants, and provide a template project consisting of multiple simulators, each with a specialized purpose, relating to a natural-disaster scenario. It will take place after the feature talks.

The SRTI is a free, open-source solution developed at the University of Michigan, and enables researchers to connect computer programs and simulators written in different languages, to share data during execution, and to design hybrid systems using disparate simulator modules, with a primary goal of being user friendly. This hands-on workshop will explain what the SRTI is, and provide an example on how to use it.

The Java Runtime Environment (JRE) is required to run the SRTI. Please install it prior to the workshop. Refer to icor.engin.umich.edu for more information on supported operating systems and languages. Participants will need to use their own computer systems at home to take part. Basic coding skills in any programming language are required.

Open to the general public. Please register if you wish to participate.

]]>
Workshop / Seminar Thu, 03 Sep 2020 16:10:17 -0400 2020-10-09T16:00:00-04:00 2020-10-09T18:00:00-04:00 Off Campus Location Michigan Institute for Computational Discovery and Engineering Workshop / Seminar Creating a Hybrid Simulation System Using the Simple Run Time Infrastructure Software
CSCS/MIDAS/MICDE Seminar | Predicting the second wave of COVID-19 in Washtenaw County, MI (October 20, 2020 11:30am) https://events.umich.edu/event/76629 76629-19733025@events.umich.edu Event Begins: Tuesday, October 20, 2020 11:30am
Location: Off Campus Location
Organized By: The Center for the Study of Complex Systems

This seminar is co-sponsored by the Michigan Institute for Computational Discovery & Engineering (MICDE) and the Michigan Institute for Data Science (MIDAS)

VIRTUAL SEMINAR LINK: myumi.ch/v2ZYv

In this work, we study and predict the spread of COVID-19 in Washtenaw County, MI through applying a discrete and stochastic network-based modeling framework. In this framework, we construct contact networks based on synthetic population datasets specific for Washtenaw County that are derived from US Census datasets. We assign individuals to households, workplaces, schools, and group quarters (such as prisons or long term care facilities). In addition, we assign casual contacts to each individual at random. Using this framework, we explicitly simulate Michigan-specific government-mandated workplace and school closures as well as social distancing measures. We perform sensitivity analyses to identify key model parameters and mechanisms contributing to the observed disease burden in the three months following the first observed cases of COVID-19 in Michigan. We then consider several scenarios for relaxing restrictions and reopening workplaces to predict what actions would be most prudent. In particular, we consider the effects of 1) different timings for reopening, and 2) different levels of workplace vs. casual contact re-engagement. Through simulations and sensitivity analyses, we explore mechanisms driving the magnitude and timing of a second wave of infections upon re-opening.

This work is based on Dr. Renardy's *paper in press* in the *Journal of Theoretical Biology* with coauthors:
Marisa Eisenberg, UM Complex Systems & Math (LSA) and Epidemiology (Public Health)
Denise Kirschner, UM Department of Microbiology & Immunology (Medical School)

]]>
Livestream / Virtual Mon, 28 Sep 2020 14:00:42 -0400 2020-10-20T11:30:00-04:00 2020-10-20T13:00:00-04:00 Off Campus Location The Center for the Study of Complex Systems Livestream / Virtual Photo of Marissa Renardy
Computational Neuroscience, Time Complexity, and Spacetime Analytics (November 10, 2020 11:10am) https://events.umich.edu/event/79206 79206-20231447@events.umich.edu Event Begins: Tuesday, November 10, 2020 11:10am
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

The proliferation of digital information in all human experiences presents difficult challenges and offers unique opportunities of managing, modeling, analyzing, interpreting, and visualizing heterogeneous data. There is a substantial need to develop, validate, productize, and support novel mathematical techniques, advanced statistical computing algorithms, transdisciplinary tools, and effective artificial intelligence apps.

Spacekime analytics is a new technique for modeling high-dimensional longitudinal data, such as functional magnetic resonance imaging (fMRI). This approach relies on extending the notions of time, events, particles, and wave functions to complex-time (kime), complex-events (kevents), data and inference-functions, respectively. This talk will illustrate how the kime-magnitude (longitudinal time order) and kime-direction (phase) affect the subsequent predictive analytics and the induced scientific inference. The mathematical foundation of spacekime calculus reveals various statistical implications including inferential uncertainty and a Bayesian formulation of spacekime analytics. Complexifying time allows the lifting of all commonly observed processes from the classical 4D Minkowski spacetime to a 5D spacetime manifold, where a number of interesting mathematical problems arise.

Spacekime analytics transforms time-varying data, such as time-series observations, into higher-dimensional manifolds representing complex-valued and kime-indexed surfaces (kime-surfaces). This process uncovers some of the intricate structure in high-dimensional data that may be intractable in the classical space-time representation of the data. In addition, the spacekime representation facilitates the development of innovative data science analytical methods for model-based and model-free scientific inference, derived computed phenotyping, and statistical forecasting. Direct neuroscience science applications of spacekime analytics will be demonstrated using simulated data and clinical observations (e.g., UK Biobank).

]]>
Presentation Thu, 05 Nov 2020 09:57:23 -0500 2020-11-10T11:10:00-05:00 2020-11-10T11:30:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Professor Ivo Dinov
Challenges in dynamic mode decomposition (November 10, 2020 11:30am) https://events.umich.edu/event/79207 79207-20231448@events.umich.edu Event Begins: Tuesday, November 10, 2020 11:30am
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Dynamic Mode Decomposition (DMD) is a powerful tool in extracting spatio-temporal patterns from multi-dimensional time series. DMD takes in time series data and computes eigenvalues and eigenvectors of a finite-dimensional linear model that approximates the infinite-dimensional Koopman operator which encodes the dynamics. DMD is used successfully in many fields: fluid mechanics, robotics, neuroscience, and more. Two of the main challenges remaining in DMD research are noise sensitivity and issues related to Krylov space closure when modeling nonlinear systems. In our work, we encountered great difficulty in reconstructing time series from multilegged robot data. These are oscillatory systems with slow transients, which decay only slightly faster than a period.
Here we present an investigation of possible sources of difficulty by studying a class of systems with linear latent dynamics which are observed via multinomial observables. We explore the influences of dataset metrics, the spectrum of the latent dynamics, the normality of the system matrix, and the geometry of the dynamics. Our numerical models include system and measurement noise. Our results show that even for these very mildly nonlinear conditions, DMD methods often fail to recover the spectrum and can have poor predictive ability. We show that for a system with a well-posed system matrix, having a dataset with more initial conditions and shorter trajectories can significantly improve the prediction. With a slightly ill-conditioned system matrix, a moderate trajectory length improves the spectrum recovery. Our work provides a self-contained framework on analyzing noise and nonlinearity, and gives generalizable insights dataset properties for DMD analysis.
Work was funded by ARO MURI W911NF-17-1-0306 and the Kahn Foundation.

]]>
Presentation Thu, 05 Nov 2020 10:02:20 -0500 2020-11-10T11:30:00-05:00 2020-11-10T11:50:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Ziyou Wu
Intro to Python for Community Members and K-12 Teachers and Students (November 10, 2020 2:45pm) https://events.umich.edu/event/79222 79222-20231462@events.umich.edu Event Begins: Tuesday, November 10, 2020 2:45pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

This hands-on workshop is tailored to audiences who do not have prior programming experience. The first half of the workshop covers Python programming basics and the second half covers performing data analysis and visualization in Python with real-world data. The audiences are encouraged to follow along with the examples on their own computer. We will use an online browser-based environment (Google Colab), and no software installations on your computer are required. Attendees will need a Google account and will sign in to their browser in order to use this cloud-based tool during the workshop.

]]>
Workshop / Seminar Thu, 05 Nov 2020 10:51:28 -0500 2020-11-10T14:45:00-05:00 2020-11-10T16:15:00-05:00 Off Campus Location Michigan Institute for Data Science Workshop / Seminar Mini-Workshop
Mini-Workshops at the MIDAS symposium (November 10, 2020 2:45pm) https://events.umich.edu/event/78763 78763-20121154@events.umich.edu Event Begins: Tuesday, November 10, 2020 2:45pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

There will be six workshops to choose from:
- Agent-based modeling and systemic racism
- Introduction to Python for community members and K-12 teachers and students
- Natural Language Processing for free text analysis
- Scrubbing and cleaning of sensitive data
- Stitching Together the Fabric of 21st Century Social Science
- Video coding and its research applications

]]>
Workshop / Seminar Thu, 22 Oct 2020 09:33:12 -0400 2020-11-10T14:45:00-05:00 2020-11-10T16:15:00-05:00 Off Campus Location Michigan Institute for Data Science Workshop / Seminar MIDAS Symposium 2020
Stitching Together the Fabric of 21st Century Social Science (November 10, 2020 2:45pm) https://events.umich.edu/event/79225 79225-20231464@events.umich.edu Event Begins: Tuesday, November 10, 2020 2:45pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Today’s pressing questions of social science and public policy demand an unprecedented degree of data scope and integration as we recognize the cross-cutting dynamics of economics, political science, sociology, demography, and psychology. This panel features four UM researchers who are pushing the frontier of data construction and linkage in coordination with partners at the U.S. Census Bureau.

]]>
Workshop / Seminar Thu, 05 Nov 2020 11:01:06 -0500 2020-11-10T14:45:00-05:00 2020-11-10T16:15:00-05:00 Off Campus Location Michigan Institute for Data Science Workshop / Seminar Mini-Workshop
Fusing Computer Vision And Space Weather Modeling (November 11, 2020 10:00am) https://events.umich.edu/event/79214 79214-20231455@events.umich.edu Event Begins: Wednesday, November 11, 2020 10:00am
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Space weather has impacts on Earth ranging from rare, immensely disruptive events (e.g., electrical blackouts caused by solar flares and coronal mass ejections) to more frequent impacts (e.g., satellite GPS interference from fluctuations in the Earth’s ionosphere caused by rapid variations in the solar extreme UV emission). Earth-impacting events are driven by changes in the Sun’s magnetic field; we now have myriad instruments capturing petabytes worth of images of the Sun at a variety of wavelengths, resolutions, and vantage points. These data present opportunities for learning-based computer vision since the massive, well-calibrated image archive is often accompanied by physical models. This talk will describe some of the work that we have been doing to start integrating computer vision and space physics by learning mappings from one image or representation of the Sun to another. I will center the talk on a new system we have developed that emulates parts of the data processing pipeline of the Solar Dynamics Observatory’s Helioseismic and Magnetic Imager (SDO/HMI). This pipeline produces data products that help study and serve as boundary conditions for solar models of the energetic events alluded to above. Our deep-learning-based system emulates a key component hundreds of times faster than the current method, potentially opening doors to new applications in near-real-time space weather modeling. In keeping with the goals of the symposium, however, I will focus on some of the benefits close collaboration has enabled in terms of understanding how to frame the problem, measure success of the model, and even set up the deep network.

]]>
Presentation Thu, 05 Nov 2020 10:27:08 -0500 2020-11-11T10:00:00-05:00 2020-11-11T10:20:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation David Fouhey
Decoding the Environment of Most Energetic Sources in the Universe (November 11, 2020 10:20am) https://events.umich.edu/event/79215 79215-20231456@events.umich.edu Event Begins: Wednesday, November 11, 2020 10:20am
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Astrophysics has always been at the forefront of data analysis. It has led to advancements in image processing and numerical simulations. The coming decade is bringing qualitatively new and larger datasets than ever before. The next generation of observational facilities will produce an explosion in the quantity and quality of data for the most distant sources, such as the first galaxies and first quasars. Quasars are the most energetic objects in the universe, reaching luminosity up to 10^14 that of the Sun. Their emission is powered by giant black holes that convert matter into energy according to the famous Einstein’s equation E = mc^2. The largest progress will occur in quasar spectroscopy. Detailed measurements of spectrum of quasar light, as it is being emitted near the central black hole and partially absorbed by clouds of gas on the way to the observer on Earth, allows for a particularly powerful probe of quasar environment. Because spectra of different chemical elements are unique, spectroscopy allows to study not only the overall properties of matter such as density and temperature, but also the detailed chemical composition of the intervening matter. However, the interpretation of these spectra is made very challenging by the many sources contributing to the absorption of light. In order to take a full advantage of this new window into the nature of supermassive black holes we need detailed theoretical understanding of the origin of quasar spectral features. In a MIDAS PODS project we are applying machine learning to model and extract such features. We are training the models using data from the state-of-the-art numerical simulations of the early universe. This approach is fundamentally different from traditional astronomical data analysis. We have only started learning what information can be extracted and still looking for a new framework to interpret these data.

]]>
Performance Thu, 05 Nov 2020 10:31:24 -0500 2020-11-11T10:20:00-05:00 2020-11-11T10:40:00-05:00 Off Campus Location Michigan Institute for Data Science Performance Oleg Gnedin
Fireside Chat with Eric Horvitz (November 11, 2020 11:00am) https://events.umich.edu/event/78764 78764-20121155@events.umich.edu Event Begins: Wednesday, November 11, 2020 11:00am
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Fireside Chat with Eric Horvitz, Microsoft, Chief Scientific Officer, November 11th, 11:00

]]>
Lecture / Discussion Thu, 22 Oct 2020 10:23:02 -0400 2020-11-11T11:00:00-05:00 2020-11-11T12:00:00-05:00 Off Campus Location Michigan Institute for Data Science Lecture / Discussion Eric Horvitz
MIDAS Seminar Series Presents: Eric Xing – Carnegie Mellon University (December 14, 2020 4:00pm) https://events.umich.edu/event/79453 79453-20327788@events.umich.edu Event Begins: Monday, December 14, 2020 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Professor, Computer Science, Carnegie Mellon University

Founder, CEO, and Chief Scientist, Petuum Inc.

]]>
Presentation Tue, 17 Nov 2020 17:17:42 -0500 2020-12-14T16:00:00-05:00 2020-12-14T17:00:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Eric Xing
THE CHANGING LANDSCAPE OF BIOMEDICAL DATA COLLECTIONS (December 21, 2020 4:00pm) https://events.umich.edu/event/79454 79454-20327789@events.umich.edu Event Begins: Monday, December 21, 2020 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Abstract:

The landscape of biomedical data is incredibly complex, rich, and rapidly changing, especially as we navigate the influx of data from the COVID-19 pandemic. More and more data is moving to the cloud, both existing and newly generated, with multiple cloud providers adding to the complexity. The data includes Electronic Health Records (EHRs), genomic data, and imaging/sensed data (e.g., pictures of tumors, lungs, cells, gas chromatographs), and all this data is enabling us to delve much deeper into complex biological concepts, for example, the relationship between phenotypes and genotypes. The NHLBI BioData Catalyst project is one example of a coordinated effort to move vast amounts of data into the cloud, navigating the complexities of data ingestion, diverse and widespread teams, and multiple cloud providers/environments.

On top of the massive shift to being able to apply huge amounts of data to better understand individuals, populations and, ultimately, life itself, we need a way to organize all this information. The activities in the NCATS Biomedical Data Translator project can be viewed as a constantly evolving analysis of the relationships of disparate data sets. In a sense, Translator is like Google for searching biomedical data.

My talk will introduce both projects and their respective impacts on biomedical research.

Bio:

Dr. Stan Ahalt is the Director of the Renaissance Computing Institute (RENCI) at UNC-Chapel Hill. As Director, he leads a team of research scientists, software and network engineers, data science specialists, and visualization experts who work closely with faculty research teams at UNC, Duke, NCSU, and partners across the country. Dr. Ahalt is also a Professor in UNC’s Department of Computer Science and the Associate Director of Informatics and Data Science (IDSci) in the North Carolina Translational and Clinical Sciences Institute (NC TraCS), UNC’s CTSA award; in this role, Dr. Ahalt leverages the expertise and resources of RENCI to foster clinical and translational research across UNC’s campus. Dr. Ahalt earned his Ph.D. in Electrical and Computer Engineering from Clemson University and has over 30 years of experience in data science, signal and image processing, and pattern recognition/ML.

]]>
Presentation Mon, 23 Nov 2020 12:01:11 -0500 2020-12-21T16:00:00-05:00 2020-12-21T17:00:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Stan Ahalt
KNOWLEDGE EXTRACTION TO ACCELERATE SCIENTIFIC DISCOVERY (January 18, 2021 4:00pm) https://events.umich.edu/event/79534 79534-20373071@events.umich.edu Event Begins: Monday, January 18, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

To combat COVID-19, clinicians and scientists all need to digest the vast amount of relevant biomedical knowledge in literature to understand the disease mechanism and the related biological functions. The first challenge is quantity. For example, nearly 2.7K new papers are published at PubMed per day. This knowledge bottleneck causes significant delay in the development of vaccines and drugs for COVID-19. The second challenge is quality due to the rise and rapid, extensive publications of preprint manuscripts without pre-publication peer review. Many research results about coronavirus from different research labs and sources are redundant, complementary or event conflicting with each other.

Let’s consider drug repurposing as a case study. Besides the long process of clinical trial and biomedical experiments, another major cause for the long process is the complexity of the problem involved and the difficulty in drug discovery in general. The current clinical trials for drug re-purposing mainly rely on symptoms by considering drugs that can treat diseases with similar symptoms. However, there are too many drug candidates and too much misinformation published from multiple sources. In addition to a ranked list of drugs, clinicians and scientists also aim to gain new insights into the underlying molecular cellular mechanisms on Covid-19, and which pre-existing conditions may affect the mortality and severity of this disease.

To tackle these two challenges, we have developed a novel and comprehensive knowledge discovery framework, COVID-KG, to accelerate scientific discovery and build a bridge between clinicians and biology scientists. COVID-KG starts by reading existing papers to build multimedia knowledge graphs (KGs), in which nodes are entities/concepts and edges represent relations involving these entities, extracted from both text and images. Given the KGs enriched with path ranking and evidence mining, COVID-KG answers natural language questions effectively. Using drug repurposing as a case study, for 11 typical questions that human experts aim to explore, we integrate our techniques to generate a comprehensive report for each candidate drug. Preliminary assessment by expert clinicians and medical school students show our generated reports are informative and sound. I will also talk about our ongoing work to extend this framework to other domains including molecular synthesis and agriculture.

Bio:

Heng Ji is a professor at Computer Science Department, and an affiliated faculty member at Electrical and Computer Engineering Department of University of Illinois at Urbana-Champaign. She is also an Amazon Scholar. She received her B.A. and M. A. in Computational Linguistics from Tsinghua University, and her M.S. and Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Multimedia Multilingual Information Extraction, Knowledge Base Population and Knowledge-driven Generation. She was selected as “Young Scientist” and a member of the Global Future Council on the Future of Computing by the World Economic Forum in 2016 and 2017. The awards she received include “AI’s 10 to Watch” Award by IEEE Intelligent Systems in 2013, NSF CAREER award in 2009, Google Research Award in 2009 and 2014, IBM Watson Faculty Award in 2012 and 2014 and Bosch Research Award in 2014-2018, and ACL2020 Best Demo Paper Award. She was invited by the Secretary of the U.S. Air Force and AFRL to join Air Force Data Analytics Expert Panel to inform the Air Force Strategy 2030. She is the lead of many multi-institution projects and tasks, including the U.S. ARL projects on information fusion and knowledge networks construction, DARPA DEFT Tinker Bell team and DARPA KAIROS RESIN team. She has coordinated the NIST TAC Knowledge Base Population task since 2010. She has served as the Program Committee Co-Chair of many conferences including NAACL-HLT2018. She is elected as the North American Chapter of the Association for Computational Linguistics (NAACL) secretary 2020-2021. Her research has been widely supported by the U.S. government agencies (DARPA, ARL, IARPA, NSF, AFRL, DHS) and industry (Amazon, Google, Bosch, IBM, Disney).

]]>
Performance Mon, 23 Nov 2020 09:48:55 -0500 2021-01-18T16:00:00-05:00 2021-01-18T17:00:00-05:00 Off Campus Location Michigan Institute for Data Science Performance Heng Li
COMPUTER VISION: WHO IS HELPED AND WHO IS HARMED? (January 25, 2021 4:00pm) https://events.umich.edu/event/79537 79537-20373074@events.umich.edu Event Begins: Monday, January 25, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Computer vision has ceased to be a purely academic endeavor. From law enforcement, to border control, to employment, healthcare diagnostics, and assigning trust scores, computer vision systems are being rapidly integrated into all aspects of society. In research, there are works that purport to determine a person’s sexuality from their social network profile images, others that claim to classify “violent individuals” from drone footage. These works were published in high impact journals, and some were presented at workshops in top tier computer vision conferences such as CVPR.

A critical public discourse surrounding the use of computer-vision based technologies has also been mounting. For example, the use of facial recognition technologies by policing agencies has been heavily critiqued and, in response, companies such as Microsoft, Amazon, and IBM have pulled or paused their facial recognition software services. Gender Shades showed that commercial gender classification systems have high disparities in error rates by skin-type and gender, and other works discuss the harms caused by the mere existence of automatic gender recognition systems. Recent papers have also exposed shockingly racist and sexist labels in popular computer vision datasets–resulting in the removal of some. In this talk, I will highlight some of these issues and proposed solutions to mitigate bias, as well as how some of the proposed fixes could exacerbate the problem rather than mitigate it.

Bio:

Timnit Gebru is a senior research scientist at Google co-leading the Ethical Artificial Intelligence research team. Her work focuses on mitigating the potential negative impacts of machine learning based systems. Timnit is also the co-founder of Black in AI, a non profit supporting Black researchers and practitioners in artificial intelligence. Prior to this, she did a postdoc at Microsoft Research, New York City in the FATE (Fairness Transparency Accountability and Ethics in AI) group, where she studied algorithmic bias and the ethical implications underlying any data mining project. She received her Ph.D. from the Stanford Artificial Intelligence Laboratory, studying computer vision under Fei-Fei Li. Prior to joining Fei-Fei’s lab, she worked at Apple designing circuits and signal processing algorithms for various Apple products including the first iPad.

]]>
Presentation Mon, 23 Nov 2020 10:00:32 -0500 2021-01-25T16:00:00-05:00 2021-01-25T17:00:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Timnit Gebru
MIDAS Seminar Series, MiCHAMP, and Precision Health Co-Present: Casey Greene, School of Medicine, University of Pennsylvania (February 22, 2021 4:00pm) https://events.umich.edu/event/81040 81040-20838682@events.umich.edu Event Begins: Monday, February 22, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Abstract:

Biomedical research disciplines are awash in data. These data, generated by new technologies as well as old approaches, provide the opportunity to systematically extract biological patterns that were previously difficult to observe. I’ll share vignettes focusing on three areas: 1) how we can use large-scale public data to better understand data for which few observations are available; 2) some work to understand why large-scale integrative analyses are beneficial; and 3) how machine learning can help to produce more datasets suitable for integration while maintaining participant privacy.

Dr. Casey Greene is an Associate Professor of Systems Pharmacology and Translational Therapeutics in the Perelman School of Medicine at the University of Pennsylvania and the Director of the Childhood Cancer Data Lab, powered by Alex’s Lemonade Stand Foundation. His lab develops machine learning methods that integrate distinct large-scale datasets to extract the rich and intrinsic information embedded in such integrated data. This approach reveals underlying principles of genetics, cellular environments, and cellular responses to that environment. Casey’s devotion to the analysis of publicly available data doesn’t stop in the lab. In 2016, Casey established the “Research Parasite Awards” after an editorial in the New England Journal of Medicine deemed scientists who analyze other scientists’ data “research parasites.” These honors, accompanied by a cash prize, are awarded to scientists who rigorously reanalyze other people’s data to learn something new.

]]>
Presentation Thu, 28 Jan 2021 09:51:43 -0500 2021-02-22T16:00:00-05:00 2021-02-22T17:00:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Casey Greene
Anil Yildirim (Aerospace Engineering) and Jiale Tan (Epidemiology) (February 25, 2021 4:00pm) https://events.umich.edu/event/81478 81478-20895806@events.umich.edu Event Begins: Thursday, February 25, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Computational Discovery and Engineering

ANIL YILDIRIM: Anil Yildirim is a PhD candidate in Aerospace Engineering and Scientific Computing. His research focuses on the development and application of robust computational tools in the context of multidisciplinary design optimization for aircraft configurations.

"ROBUST AND HIGH-PERFORMANCE TOOLS FOR MULTIDISCIPLINARY DESIGN OPTIMIZATION": The development of future sustainable aircraft heavily relies on the design and integration of advanced propulsion systems. However, the design of these systems are challenging due to the tightly coupled interactions between the aerodynamic and the propulsion disciplines. My research focuses on enabling these advanced technologies using aeropropulsive design optimization, in which the aerodynamic and propulsion system designs are optimized in a coupled manner. In this process, I use multiple robust and high-performance computational tools including the computational fluid dynamics (CFD) solver we have been developing in the MDO Lab at the University of Michigan. In this talk, I will cover some recent advancements in the field of CFD-based aeropropulsive design optimization and the computational methodologies we have been using for this work.

JIALE TAN: Jiale is a second year Phd student working with Prof. Rafael Meza in Epidemiology. His interest is to apply computational skills to public health challenges so that he can develop and apply modeling techniques for infectious and noninfectious diseases, including for viral infections like HIV and HCV, and eventually use them for modeling non-communicable diseases that disproportionately affect global health like cancer.

"MARKOV MULTISTATE TRANSITION MODEL ON ELECTRONIC NICOTINE DELIVERY SYSTEMS AND TRADITIONAL CIGARETTES": Electronic nicotine delivery systems (ENDS) have dramatically changed the landscape of tobacco products patterns in the USA since 2011. The impact of ENDS use on traditional cigarettes smoking remains a topic of considerable debate. A Markov multistate transition model was used to estimate transition rates (Hazard rate) between ENDS and cigarette use states (25 use states); never user, non-current experimental user, non-current regular user, current experimental user, and current regular user for each product. A 25×25 transition matrix was generated from this model. Parallel computations using 150 processors was used to estimate the transition rates. The Population Assessment of Tobacco and Health study, which includes longitudinal data from 11,475 youth of ages 12 to 24 years from 2013-2018 was used to calibrate the model. The hazard estimates show the patterns of ENDS and cigarette use experimentation and transition to regular use. Next steps will assess the impact of different sociodemographic covariates (age, sex, race, education, household income) on the estimated transition rates.

Register to receive Zoom information: https://umich.zoom.us/meeting/register/tJUtce2gqDkuE9chnr5NMrBGjYgeXsl-fyJX

]]>
Workshop / Seminar Thu, 28 Jan 2021 17:13:06 -0500 2021-02-25T16:00:00-05:00 2021-02-25T17:00:00-05:00 Off Campus Location Michigan Institute for Computational Discovery and Engineering Workshop / Seminar A. Yildirim and J. Tan
MIDAS Seminar Series and Michigan AI Initiative Co-Present: Heng Ji, University of Illinois Urbana Champaign (March 8, 2021 4:00pm) https://events.umich.edu/event/81082 81082-20846538@events.umich.edu Event Begins: Monday, March 8, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

To combat COVID-19, clinicians and scientists all need to digest the vast amount of relevant biomedical knowledge in literature to understand the disease mechanism and the related biological functions. The first challenge is quantity. For example, nearly 2.7K new papers are published at PubMed per day. This knowledge bottleneck causes significant delay in the development of vaccines and drugs for COVID-19. The second challenge is quality due to the rise and rapid, extensive publications of preprint manuscripts without pre-publication peer review. Many research results about coronavirus from different research labs and sources are redundant, complementary or event conflicting with each other.

Let’s consider drug repurposing as a case study. Besides the long process of clinical trial and biomedical experiments, another major cause for the long process is the complexity of the problem involved and the difficulty in drug discovery in general. The current clinical trials for drug re-purposing mainly rely on symptoms by considering drugs that can treat diseases with similar symptoms. However, there are too many drug candidates and too much misinformation published from multiple sources. In addition to a ranked list of drugs, clinicians and scientists also aim to gain new insights into the underlying molecular cellular mechanisms on Covid-19, and which pre-existing conditions may affect the mortality and severity of this disease.

To tackle these two challenges, we have developed a novel and comprehensive knowledge discovery framework, COVID-KG, to accelerate scientific discovery and build a bridge between clinicians and biology scientists. COVID-KG starts by reading existing papers to build multimedia knowledge graphs (KGs), in which nodes are entities/concepts and edges represent relations involving these entities, extracted from both text and images. Given the KGs enriched with path ranking and evidence mining, COVID-KG answers natural language questions effectively. Using drug repurposing as a case study, for 11 typical questions that human experts aim to explore, we integrate our techniques to generate a comprehensive report for each candidate drug. Preliminary assessment by expert clinicians and medical school students show our generated reports are informative and sound. I will also talk about our ongoing work to extend this framework to other domains including molecular synthesis and agriculture.

Bio:

Heng Ji is a professor at Computer Science Department, and an affiliated faculty member at Electrical and Computer Engineering Department of University of Illinois at Urbana-Champaign. She is also an Amazon Scholar. She received her B.A. and M. A. in Computational Linguistics from Tsinghua University, and her M.S. and Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Multimedia Multilingual Information Extraction, Knowledge Base Population and Knowledge-driven Generation. She was selected as “Young Scientist” and a member of the Global Future Council on the Future of Computing by the World Economic Forum in 2016 and 2017. The awards she received include “AI’s 10 to Watch” Award by IEEE Intelligent Systems in 2013, NSF CAREER award in 2009, Google Research Award in 2009 and 2014, IBM Watson Faculty Award in 2012 and 2014 and Bosch Research Award in 2014-2018, and ACL2020 Best Demo Paper Award. She was invited by the Secretary of the U.S. Air Force and AFRL to join Air Force Data Analytics Expert Panel to inform the Air Force Strategy 2030. She is the lead of many multi-institution projects and tasks, including the U.S. ARL projects on information fusion and knowledge networks construction, DARPA DEFT Tinker Bell team and DARPA KAIROS RESIN team. She has coordinated the NIST TAC Knowledge Base Population task since 2010. She has served as the Program Committee Co-Chair of many conferences including NAACL-HLT2018. She is elected as the North American Chapter of the Association for Computational Linguistics (NAACL) secretary 2020-2021. Her research has been widely supported by the U.S. government agencies (DARPA, ARL, IARPA, NSF, AFRL, DHS) and industry (Amazon, Google, Bosch, IBM, Disney).

]]>
Presentation Mon, 25 Jan 2021 17:32:08 -0500 2021-03-08T16:00:00-05:00 2021-03-08T17:00:00-05:00 Off Campus Location Michigan Institute for Data Science Presentation Heng Li
MIDAS Seminar Series Presents: Patricia Murrieta-Flores, Lancaster University (March 15, 2021 4:00pm) https://events.umich.edu/event/82623 82623-21147749@events.umich.edu Event Begins: Monday, March 15, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

The field of Digital Humanities, and particularly the increasing accessibility of digital resources, has opened a significant number of opportunities for the study of sources that can be highly relevant to history and archaeology. These opportunities include the use of methodologies from the fields of Artificial Intelligence and Computational Linguistics and the application of a diversity of techniques and methods for the large-scale analysis and exploration of collections of historical documents.

In the case of the early colonial history of Mexico, there is an enormous variety of historical documents related to the economic, social and political life at that time. An example of this is the sixteenth-century Relaciones Geográficas de Nueva España (the Geographic Reports of New Spain). Created from the responses to a questionnaire ordered by Philip II’s and obtained between 1577 and 1585, the Geographic Reports sought to compile all the information available on the American territories under Spanish rule. Due to its essential content, these reports have been the object of study by a large number of researchers, and are frequently used in the analysis of the political, social, territorial and economic situation at the time. Although numerous studies seek to understand the shifting territorial situation in New Spain, two enormous challenges have remained. The first one is the considerable size or volume of information to be analysed and compared. The second has been the precise identification of the places mentioned in these reports, especially on a large scale.

In this presentation, I will introduce the project sponsored by the Transatlantic Platform for the Humanities and Social Sciences (T-AP) called “Digging into Early Colonial Mexico: a large-scale computational analysis of historical documents”, and some of its results. Taking as a basis the historical corpus of the Geographic Reports of New Spain, the project main objectives have been: 1) to adapt and develop techniques from Artificial Intelligence, including aspects of Natural Language Processing, Text Mining and Geographic Information Systems for the extraction and analysis of historical information from this source, and 2) to design computational methodologies for the identification of possible large-scale historical patterns. This research is allowing us to clarify some of the essential geographic questions related to the period and the colonial situation in this territory. I will also present a methodology termed Geographical Text Analysis and some of the most critical outputs from this project. These include software developed to carry out this type of analysis, the first sixteenth-century digital gazetteer of Mexico and Guatemala, and the first experiments using Natural Language Processing to automatically annotate the Relaciones corpus.

]]>
Presentation Mon, 01 Mar 2021 13:19:07 -0500 2021-03-15T16:00:00-04:00 2021-03-15T17:00:00-04:00 Off Campus Location Michigan Institute for Data Science Presentation Patricia Murrieta-Flores
MIDAS Seminar Series and Michigan AI Initiative Co-Present: Mona Diab, Computer Science, George Washington University (March 22, 2021 4:00pm) https://events.umich.edu/event/81039 81039-20838681@events.umich.edu Event Begins: Monday, March 22, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

Advances in machine learning have led to quite fluent natural language generation technologies. Most of our current optimizations and evaluations focus on accuracy in output. Faithful generation is considered a nice to have, a luxury. In this talk I make the argument that faithful generation is crucial to our generation technologies especially given the scale and impact NLP technologies have on people’s lives.

Mona Diab is a Full Professor of Computer Science at the George Washington University where she directs the Care4Lang NLP lab. She is also Research Scientist with Facebook AI. She conducts research in Statistical Natural Language Processing (NLP) is a rapidly growing, exciting field of research in artificial intelligence and computer science. Interdisciplinarity is inherent to NLP, drawing on the fields of computer algorithms, software engineering, statistics, machine learning, linguistics, pragmatics, information technology, etc. In NLP, researchers model language and its use, and build both analytical models and predictive ones. In Professor Diab’s NLP lab, they address problems in social media processing, building robust enabling technologies such as syntactic and semantic processing tools for written texts in different languages, information extraction tools for large data, multilingual processing, machine translation, and computational sociolinguistic processing. Professor Diab has a special interest in Arabic NLP, where the emphasis has been on investigating Arabic dialect processing where there are very few available automated resources.

]]>
Presentation Tue, 09 Feb 2021 11:13:10 -0500 2021-03-22T16:00:00-04:00 2021-03-22T17:00:00-04:00 Off Campus Location Michigan Institute for Data Science Presentation Mona Diab
MIDAS Seminar Series Presents: Anne Plant, NIST Fellow, National Institute of Standards and Technology (March 29, 2021 4:00pm) https://events.umich.edu/event/82212 82212-21054518@events.umich.edu Event Begins: Monday, March 29, 2021 4:00pm
Location: Off Campus Location
Organized By: Michigan Institute for Data Science

While reproducibility can be an important hallmark of good science, it is not often the most important indicator. The discipline of metrology, or measurement science, describes a measurement result as a value and the uncertainty around that value. We propose a systematic process for considering the sources of uncertainty in a scientific study that can be applied to virtually all

disciplines of scientific research. We suggest that a research study can be characterized by how sources of uncertainty in the study are reported and mitigated. This approach provides a path for sharing experimental data on complex systems such as biological network processes. A serious challenge for such studies involves collecting experimental metadata and protocol details.

Bio:

Dr. Plant is currently a NIST Fellow, focusing on cell imaging and theoretical frameworks for understanding complex biological response in cells. She is an ex officio member of the NIBIB National Advisory Council, a Fellow of the AIMBE, and an AAAS Fellow. She previously served as Chief of the Biosystems and Biomaterials Division at NIST, and in the White House Office of Science and Technology Policy.

]]>
Workshop / Seminar Wed, 24 Feb 2021 11:02:58 -0500 2021-03-29T16:00:00-04:00 2021-03-29T17:00:00-04:00 Off Campus Location Michigan Institute for Data Science Workshop / Seminar Anne Plant