News

Nick McGreivy: working at the intersection of machine learning and plasma physics
Sept. 15, 2021
Nick McGreivy is interested using machine learning as a tool to accelerate the computational simulation of partial differential equations in plasma physics. “Plasma physicists have spent a lot of time and effort developing equations that describe the behavior of plasma within a nuclear fusion reactor,” said McGreivy. “One problem that I am working on is that often those equations take a really long time to solve. The goal is to speed that process up dramatically, maybe even by a couple of orders of magnitude, through a clever application of machine learning. And then that will allow us to test much more quickly and a much wider range of different possible scenarios, which would be useful for the optimization of future fusion reactors.”
Christopher Barkachi: using data science to build an e-learning marketplace
Aug. 26, 2021
Author
Written by Sharon Adarlo
Barkachi is interested in using data science techniques for practical applications and having it potentially spun off into a start-up business. His independent project for the CSML certificate was developed along those lines: an e-learning market place called LiveShare.
Christina Kreisch: using machine learning tools to probe the universe’s evolution
Aug. 17, 2021
Author
Written by Sharon Adarlo
Kreisch research interests lie in cosmology, a branch of astronomy that concerns itself with the universe’s origin and its evolution. She marries this interest with machine learning, which scientists have increasingly come to rely in recent years in order to interpret cosmological data. “I work at the intersection of theory and computation and cosmology,” said Kreisch. Her thesis is made up of three parts. The first part is theory and computationally-driven and concerns itself with neutrinos and their interactions in the early universe. This research, “The Neutrino Puzzle: Anomalies, Interactions, and Cosmological Tensions,” appeared in the journal Physical Review D in April 2019 and garnered 170 citations. Kreisch is first author.
Latest CSML newsletter is published
Aug. 11, 2021
Since our last newsletter, the Center for Statistics and Machine Learning has been a hive of activity and growth, despite a pandemic hampering many in-person engagements. We marked the end of the spring semester with our annual poster session and were pleased to celebrate the accomplishments of 100 undergraduates and 16 graduate students earning SML certificates. Other notable events included new faculty joining the center, the publication of exciting research, enriching online events, and the expansion of educational opportunities for students and the larger data science community on campus. Check out our highlights below.
Ten Research Projects Receive DataX Funding
Aug. 4, 2021
Author
Written by Sharon Adarlo
Ten new interdisciplinary research projects have won funding from Princeton University’s Schmidt DataX Fund, with the goal of spreading and deepening the use of artificial intelligence and machine learning across campus in order to accelerate discovery. The 10 faculty projects, supported through a major gift from Schmidt Futures, involve 19 researchers and several departments and programs, from computer science to politics. The projects explore a variety of subjects, including an analysis of how money and politics interact, discovering and developing new materials exhibiting quantum properties, and advancing natural language processing through the automatic construction of novel knowledge bases.
Alan Ding: using data science to probe political polarization on Twitter
July 26, 2021
Author
Written by Sharon Adarlo
In his independent project for the CSML certificate, Alan Ding decided to look into the deeply polarizing COVID-19 discourse on Twitter. He wanted to analyze any trends and see if it was possible to ameliorate polarization on the social media platform.
Francisco Carrillo: using machine learning to study fluid dynamics
July 21, 2021
Author
Written by Sharon Adarlo
Francisco Carrillo’s main research focus is on computational fluid dynamics, specifically flow of fluid material through a deformable porous medium such as fine-grained soils and sedimentary rocks.
Timothy D. Kim: working at the intersection of machine learning and neuroscience
July 15, 2021
Author
Written by Sharon Adarlo

Timothy D. Kim, 28, doctoral student

Studies:

Kim is a doctoral student at the Princeton Neuroscience Institute, where he has been since 2015. He also recently completed the graduate certificate program at the Center for Statistics and Machine Learning…

Roshini Balasubramanian: developing neural networks for medicine
July 7, 2021
Author
Written by Sharon Adarlo
In the summer after her freshman year, Roshini Balasubramanian interned at Children’s National Health System, a non-profit pediatric healthcare provider, through Princeton Internships in Civic Service. It was during this internship where she witnessed firsthand the transformational power of big data in healthcare. Healthcare practitioners were using data science to track patients and uncover new insights in other medical data they were collecting.
Anthony Cilluffo: using data science to enhance public policy
July 2, 2021
Author
Written by Sharon Adarlo
Anthony Cilluffo tackled a thorny and hot button subject for his research project: police misconduct. “Police departments are grappling with how to respond to public demands for accountability and reform. One way to improve policing is to provide targeted training to officers most likely to commit actions that breach the public’s trust in police,” he said. In order find police officers who could benefit from additional training, he turned to data science. He took a public data set of NYPD complaints from the 1980s to 2019 and developed a model to predict officers most likely to have a substantiated complaint against them. “I trained random forest and naive Bayes classifiers for this task,” said Cilluffo about some of the data science techniques he used. “Overall, the results using publicly available data offer a promising view of the possible results using more detailed personnel data inside the NYPD.”