Spring 2020 TWed Virtual Lightning Talks

Plan to join us for a very, VERY special TWed as the Tetherless World Constellation holds a "virtual" version of our end-of-term Graduate Research "Lightning Talks." TWed Lightning Talks are a great way for the TWC community and friends to learn of the wide range of amazing research happening in the Tetherless World, and "a good time is had by all!"

Privacy Preserving Synthetic Health Data Generation and Evaluation erickj4 Wed, 04/22/2020 - 19:49

Attempting to use real medical data in a classroom setting is hard to do without limiting yourself to specific datasets. Through the research being presented we work to create an end-to-end workflow for generating synthetic health data and testing the synthetic data for privacy, resemblance, and utility. This includes creating a novel generation method called HealthGAN and defining metrics for measuring the privacy and resemblance of the generated data. The utility of the data is then measured in the context of the analysis task the dataset was designed to accomplish.

Malik Magdon-Ismail

Dr. Magdon-Ismail has been a Professor of Computer Science since 2000. After degrees at Yale and Caltech, Dr. Magdon-Ismail was a research scholar at Caltech before joining Rensselaer as Assistant Professor of Computer Science. His interests are in decision making from data in complex systems, including machine learning, computational finance and social and communication networks. He enjoys poker, bridge, squash, tennis and badminton. For a full bio and more details, please visit his web page.

Education

B.S., Physics, Yale University, 1993. M.S., Physics California Institute of Technology, 1995. PhD., EE/Physics, California Institute of Technology, 1998.

Focus Area

Learning from Data; theory and applications., Computational Finance, Social and Communication Networks; Hidden Groups., Inference and Search on Volunteer Computing Platforms, Collective Wisdom in Multi-agent Systems; Prediction Markets.

Selected Scholarly Works

Malik Magdon-Ismail, "Permutation Complexity Bound on Out-Sample Error", Proc. 24th Annual Conference on Neural Information Processing Systems (NIPS), 2010.

Costas Busch, Malik Magdon-Ismail "Atomic Routing Games on Maximum Congestion", Theoretical Computer Science, Volume 410, Issue 36, Pages 3337-3347, 2009.

Malik Magdon-Ismail, Konstantin Mertsalov, "A Permutation Approach to Validation", Proc. 10th SIAM International Conference on Data Mining (SDM), pages 882-983, Columbus Ohio, April 29-May 1, 2010.

Sanmay Das, Malik Magdon-Ismail, "Collective Wisdom: Information Growth in Wikis and Blogs", ACM Conference on E-Commerce (EC 2010), pages 231-240, June 7-8 , Cambridge Massachusetts, 2010.

Costas Busch, Malik Magdon-Ismail, Marios Mavronicolas, "Universal Bufferless Packet Switching", Siam Journal on Computing, Volume 37, Issue 4, pages 1139-1162, 2007.

Malik Magdon-Ismail, and Joseph Sill "A Linear Fit Gets the Correct Monotonicity Directions", Machine Learning, Volume 70, Number 1 / January, 2008, pages 21-43.

Volkan Isler, Malik Magdon-Ismail "Sensor Selection in Arbitrary Dimension", IEEE Transactions on Automation Science and Engineering (TASE), Vol. 5, No. 4, pages 651-660, 2008.

Ali Civril, Malik Magdon-Ismail "On Selecting a Maximum Volume Sub-Matrix of a Matrix and Related Problems", Theoretical Computer Science, 2009.

Nathan Cole, Heidi Joe Newberg, Malik Magdon-Ismail, Travis Desell, Kristopher Dawsey, Warren Hayashi, Xinyang (Fred) Liu, Jonathan Purnell, Boleslaw Szymanski, Carlos Varela, James Wisniewski, "Maximum Likelihood Fitting of Tidal Streams with application to the Sagittarius Dwarf Tidal Tails", the Astrophysical Journal, Vol 683, pages 750-766 (2008).

Jeffery Baumes, Mark Goldberg, Mykola Hayvonovych, Malik Magdon-Ismail, William Wallace, Mohammed Zaki, "Finding Hidden Group Structure in a Stream of Communications", <strong>[Top 3 Paper Award]</strong>, Proceedings of the 4th Symposium on Intelligence and Security Informatics (ISI 06), San Diego, CA, May 23-24 2006.
IDEA Webinar: "COVIDMINDER: Revealing regional disparities in outcomes, determinants, and mediations of the COVID-19 pandemic" erickj4 Wed, 04/15/2020 - 17:44
COVIDMINDER examines how and why COVID-19 impacts regions differently. Using daily updated data, COVIDMINDER compares community risks, mediation tools, and outcomes related to COVID-19 by state across the United States, and by county within New York state.

First Annual Cognitive and Immersive Data Insights Application Challenge (June 5–6, 2018)

On June 5-6, 2018 The Lally School of Management, the Rensselaer Institute for Data Exploration and Applications (IDEA) / Health INCITE, the Center for Global Communication+Design (Comm+D), and the Cognitive and Immersive Systems Lab (CISL) presented the 2018 Rensselaer Cognitive and Immersive Data Insights Application Challenge. More than 40 RPI undergrad and grad students competed in this inaugural challenge to create immersive, multimodal, collaborative applications using health and business datasets.

Marjorie McShane

Marjorie McShane develops cognitive models of intelligent agents that can collaborate with people in task-oriented, dialog applications. While at heart a linguist, she is particularly interested in the integration of functionalities that are often treated in isolation, such as physiological simulation, emotion modeling, and the many aspects of cognition. 

One aspect of cognition to which she has devoted particular attention is natural language processing, approached from a cross-linguistic perspective and with the goal of producing machine-tractable descriptions that can support sophisticated conversational agents. She has also worked extensively on cognitive modeling in the medical domain, to support the configuration of intelligent agents playing the roles of virtual patients and tutors in training applications such as the Maryland Virtual Patient system.

McShane has (co-)authored three books: Linguistics for the Age of AI (MIT Press, 2021), A Theory of Ellipsis (Oxford University Press, 2005), and An Innovative, Practical Approach to Polish Inflection (Lincom Europa, 2003). She has published extensively on linguistics, natural language processing, cognitive modeling, and knowledge representation.

Education

PhD, Slavic Languages and Literatures, Princeton University

Focus Area

linguistics, cognitive modeling, natural language processing