Upcoming Events

Jan
25
2021

Data Science Nights - January 2021 Meeting (Speaker: Bryan Pardo)

5:15 PM

JANUARY MEETING: Wednesday, January 27, 2021 at 5:15pm (Central) via Zoom and Gather

DATA SCIENCE NIGHTS are monthly hack nights on popular data science topics, organized by Northwestern University graduate students and scholars. Aspiring, beginning, and advanced data scientists are welcome!

AGENDA:

5:15: Welcome to Data Science Nights via Zoom
* Zoom Link: https://northwestern.zoom.us/j/96207323991
* Passcode: DSN2021
5:30: Presentation by Bryan Pardo, Northwestern University
6:00: Hacking session via Gather
* Gather link: https://gather.town/app/UCTJAHOgQi2FLx4O/DSN

SPEAKER: Bryan Pardo, Associate Professor, McCormick School of Engineering, Northwestern University

TOPIC: New directions in deep audio source separation: training without ground truth and automatic model selection

Audio source separation is the task of separating an audio scene containing multiple concurrent sound sources into individual streams/tracks, each containing a source (or group of sources) of interest to the user.  Source separation is an enabling technology for a variety of tasks, including speech recognition, music transcription, sound object ID, and hearing assistance.  Deep learning models are the state-of-the-art in source separation, but they are typically trained on synthetic audio mixtures made from isolated sound source recordings so that ground-truth for the separation is known. However, the vast majority of available audio is not isolated, limiting the range of scenes where deep models trained on isolated data are effective.  Furthermore, a deep model is typically only successful in separating audio mixtures similar to the mixtures it was trained on.  This requires the end user to know enough about each model’s training to select the correct model for a given audio mixture. In this talk, Prof. Pardo will outline proposed solutions to both problems. First, he will present a method to train a deep source separation model in an unsupervised way by bootstrapping using multiple primitive cues, without the need for ground truth isolated sources or artificial training mixtures.  He will then outline a proposed confidence measure that can be broadly applied to any clustering-based source separation model. The proposed confidence measure does not require ground truth to estimate the quality of a separated source. This allows automatic selection of the appropriate deep clustering model for an audio mixture.

SPEAKER BIO: Bryan Pardo is head of Northwestern University’s Interactive Audio Lab and co-director of the Northwestern University HCI+Design institute. Prof. Pardo has appointments in in the Department of Computer Science and Department of Radio, Television and Film. He received a M. Mus. in Jazz Studies in 2001 and a Ph.D. in Computer Science in 2005, both from the University of Michigan. He has authored over 100 peer-reviewed publications. He has developed speech analysis software for the Speech and Hearing department of the Ohio State University, statistical software for SPSS and worked as a machine learning researcher for General Dynamics. He has collaborated on and developed technologies acquired and patented by companies like Bose, Adobe and Ear Machine. While finishing his doctorate, he taught in the Music Department of Madonna University. When he is not teaching or researching, he performs on saxophone and clarinet with the bands Son Monarcas and The East Loop.

For more info: data-science-nights.org

Supporting Groups:

This event is supported by the Northwestern Institute for Complex Systems and the Northwestern Data Science Initiative.

Jan
27
2021

WED@NICO WEBINAR: Irena Vodenska, Boston University

12:00 PM

Speaker:

Irena Vodenska, Associate Professor in Finance, Director, Finance Programs, Metropolitan College, Boston University

Title:

A bird’s-eye view into the origin of systemic risk: Financial Institutions, Sovereign Debt, and Public Health and Policy

Abstract:

As economic entities become increasingly interconnected, shocks in financial and economic networks can provoke significant cascading failures throughout the system. To study systemic risk, we model financial institutions' relationships, economic dependencies, and production flows to propose a cascading failure model describing the risk propagation process during crises. We find that our model efficiently identifies a significant portion of the failed banks reported by the Federal Deposit Insurance Corporation during the Global Financial Crisis of 2008. We also study the European sovereign debt crisis of 2009-2012 and observe that the results closely match real-world events (e.g., the high risk of Greek sovereign bonds and Greek banks' distress). We propose an institutional, systemic importance ranking, BankRank, for the financial institutions analyzed in the European bank study to assess individual banks' contribution to the overall systemic risk. Finally, we propose a dynamic cascade model to investigate the systemic risk posed by sector level industries within the U.S. inter-industry network. We then use this model to study the effect of the disruption presented by COVID-19 during 2020 on the U.S. economy. We impose an initial shock that disrupts one or more industries' production capacity and calculates the propagation of production shortage with a modified Cobb-Douglas production function. In the case of COVID-19, the initial shock reflects the loss of labor between March and April 2020, as reported by the Bureau of Labor Statistics. These studies suggest that the cascading failure models could be useful for systemic risk stress testing for financial and economic systems. The models could become complementary to existing stress tests and scenario analysis, incorporating the contribution of the interconnectivity of the banks, governments, and industries to systemic risk in time-dependent networks.

Speaker Bio:

Irena Vodenska is an associate professor of finance and director of finance programs at Boston University’s Metropolitan College. Her research focuses on network theory and complexity science in macroeconomics. She conducts a theoretical and applied interdisciplinary research using quantitative approaches for modeling interdependencies of financial networks, banking system dynamics, and global financial crises. More specifically, Vodenska’s research focuses on modeling of early warning indicators and systemic risk propagation throughout interconnected financial and economic networks. She also studies the effects of news announcement on financial markets, corporations, financial institutions, and related global economic systems. She uses neural networks and deep learning methodologies for natural language processing to text mine important factors affecting corporate performance and global economic trends. Prof. Vodenska teaches Investment Analysis and Portfolio Management, International Finance and Trade, Financial Regulation and Ethics, and Derivatives Securities and Markets at Boston University. Vodenska holds a Ph.D. in Econophysics (Statistical Finance) from Boston University, MBA from Owen Graduate School of Management at Vanderbilt University and BS in Computer Information Systems from the University of Belgrade. She is also a Chartered Financial Analyst (CFA) charter holder. As a principal investigator (PI) for Boston University, she has won interdisciplinary research grants awarded by the European Commission (EU), Network Science Division of the US Army Research Office, and the National Science Foundation (US).

Webinar:

Webinar link: https://northwestern.zoom.us/j/94202105939
Passcode: nico
ID: 942 0210 5939

About the Speaker Series:

Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems and data science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.

Feb
03
2021

WED@NICO WEBINAR: Tina Eliassi-Rad, Northeastern University

12:00 PM

Speaker:

Tina Eliassi-Rad, Professor, Khoury College of Computer Sciences, Northeastern University

Title:

TBA

Abstract:

TBA

Speaker Bio:

Tina Eliassi-Rad is a Professor of Computer Science at Northeastern University in Boston, MA. She is also a core faculty member at Northeastern's Network Science Institute. Prior to joining Northeastern, Tina was an Associate Professor of Computer Science at Rutgers University; and before that she was a Member of Technical Staff and Principal Investigator at Lawrence Livermore National Laboratory. Tina earned her Ph.D. in Computer Sciences (with a minor in Mathematical Statistics) at the University of Wisconsin-Madison. Her research is at the intersection data mining, machine learning, and network science. She has over 100 peer-reviewed publications (including a few best paper and best paper runner-up awardees); and has given over 200 invited talks and 14 tutorials. Tina's work has been applied to personalized search on the World-Wide Web, statistical indices of large-scale scientific simulation data, fraud detection, mobile ad targeting, cyber situational awareness, and ethics in machine learning. Her algorithms have been incorporated into systems used by the government and industry (e.g., IBM System G Graph Analytics) as well as open-source software (e.g., Stanford Network Analysis Project).

Webinar:

Webinar link: https://northwestern.zoom.us/j/95878198317
Passcode: nico
ID: 958 7819 8317

About the Speaker Series:

Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems and data science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.

Feb
10
2021

WED@NICO WEBINAR: Noah Askin, INSEAD

12:00 PM

Speaker:

Noah Askin, Assistant Professor of Organisational Behaviour, INSEAD

Title:

TBA

Abstract:

TBA

Speaker Bio:

Noah Askin is an Assistant Professor of Organisational Behaviour at INSEAD in Fontainebleau. His research interests include social and cultural networks, the drivers and consequences of creativity and innovation (particularly in the music industry), the production and consumption of culture, and the dynamics of organisational and individual status. His work, which has garnered recognition on the Thinkers 50 Radar list, has appeared in Administrative Science Quarterly, American Sociological Review, computational social science publications, and been covered in the press by Rolling Stone, Forbes, Business Insider, Quartz.com, The Times of London, M Magazine, the New York Post, and music industry blogs.

Webinar:

Webinar link: https://northwestern.zoom.us/j/96945660289
Passcode: nico
ID: 969 4566 0289

About the Speaker Series:

Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems and data science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.

Feb
17
2021

WED@NICO WEBINAR: Susanna Manrubia, Spanish National Centre for Biotechnology (CSIC)

12:00 PM

Speaker:

Susanna Manrubia, Associate Professor, Spanish National Centre for Biotechnology (CSIC)

Title:

TBA

Abstract:

TBA

Speaker Bio:

Susanna Manrubia is an Associate Professor at the Spanish National Centre for Biotechnology (CSIC), in Madrid. She belongs to the Systems Biology Program, where she leads the Group of Evolutionary Systems. Her group maintains close collaborations with experimentalists and focuses on developing theoretical and computational descriptions of biological, mainly evolutionary phenomena. Professor Manrubia is also interested in cultural patterns and collective social behaviour.

Webinar:

Webinar link: https://northwestern.zoom.us/j/96887739805
Passcode: nico
ID: 968 8773 9805

About the Speaker Series:

Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems and data science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.

Feb
23
2021

Data Science Nights - February 2021 Meeting

5:15 PM

NOVEMBER MEETING: Monday, February 23, 2021 at 5:30pm (Central) via Zoom and Gather

DATA SCIENCE NIGHTS are monthly hack nights on popular data science topics, organized by Northwestern University graduate students and scholars. Aspiring, beginning, and advanced data scientists are welcome!

AGENDA:

TBA

SPEAKERAviv Landau, Postdoctoral research scientist, Data Science Institute, Columbia University

TOPIC: TBA

For more info: data-science-nights.org

Supporting Groups:

This event is supported by the Northwestern Institute for Complex Systems and the Northwestern Data Science Initiative.