Anuththara Rupasinghe
  • Bio
  • Projects
  • Publications
  • Teaching & Service
  • CV
  • Personal
  • Contact
  • Google Scholar
  • LinkedIn
  • GitHub

Anuththara Rupasinghe, Ph.D. 

Postdoctoral Research Fellow, Princeton University
Part-Time Lecturer, Rutgers University

Machine Learning | Statistical Signal Processing | Data Science | Computational Neuroscience | Biomedical AI

I am a machine learning researcher and educator with a Ph.D. in Electrical and Computer Engineering and postdoctoral research experience at the Princeton Neuroscience Institute. My research focuses on developing statistical and machine learning methods for analyzing complex neural and biological data, with an emphasis on probabilistic modeling, statistical signal processing, time-series analysis, uncertainty quantification, and interpretable inference. Alongside my research, I am passionate about teaching and mentoring students in mathematics, engineering, and computational methods.

My path has been shaped by a long-standing interest in mathematics, statistics, engineering, and data-driven scientific discovery. During my undergraduate studies in Electrical and Electronic Engineering at the University of Peradeniya, Sri Lanka, I received the Best Performance in Engineering award in 2016, along with several prizes in electrical engineering, engineering mathematics, communications, and power systems.

In 2017, I joined the Department of Electrical and Computer Engineering at the University of Maryland, College Park, supported by the Clark School of Engineering Distinguished Graduate Fellowship. There, I completed my Ph.D. under the supervision of Professor Behtash Babadi, developing Bayesian methods for neural and physiological time-series analysis. In 2022, I was selected as a Rising Star in EECS.

Since graduating in 2022, I have been a postdoctoral research fellow at Princeton University, working with Professor Jonathan Pillow. At Princeton, I develop machine learning and statistical modeling approaches for understanding neural population activity and behavior. My postdoctoral work has been recognized by the Princeton Neuroscience Institute QCN T32 Postdoctoral Fellowship Award.

In Fall 2026, I also joined Rutgers University, New Brunswick, as a Part-Time Lecturer in Biomedical Engineering, teaching BME 309: Devices and Systems, a core undergraduate course. I enjoy teaching and mentoring students, particularly in areas that connect mathematical foundations with engineering and computational applications.

Across my research, I am interested in using statistical modeling and machine learning to extract meaningful structure from high-dimensional, noisy, and temporally structured data. I enjoy developing computational methods, analyzing complex datasets, and translating mathematical ideas into practical applications. I am interested in both industry research and applied machine learning roles, including research scientist, applied scientist, data science, and biomedical AI positions, as well as teaching-focused academic opportunities where I can contribute to engineering education and student mentorship.

Research interests

  • Machine learning
  • Bayesian inference
  • Predictive modeling
  • Data science
  • Time-series analysis
  • Statistical signal processing
  • Computational neuroscience
  • Biomedical AI
  • Uncertainty quantification

Teaching interests

I am passionate about teaching and mentoring students, particularly in subjects that connect mathematical foundations with computational and engineering applications. My teaching interests include probability and statistics, signals and systems, statistical signal processing, machine learning, Bayesian inference, and computational methods.

For more details, see my Teaching, Mentoring & Service page.

Selected Highlights

2026

Joined Rutgers University, New Brunswick, as a Part-Time Lecturer in Biomedical Engineering, teaching the undergraduate course BME 309: Devices and Systems.

2026

Continuous Multinomial Logistic Regression accepted at ICLR 2026.

2026

Continuous partitioning of neuronal variability published in eLife.

2025

Patchy harmonic functional connectivity of the mouse auditory cortex published in PNAS.

2024

Received the Princeton Neuroscience Institute QCN T32 Postdoctoral Fellowship Award.

2024

Received the SfN Trainee Professional Development Award.

2022

Started as a Postdoctoral Researcher at Princeton University, Princeton Neuroscience Institute.

2022

Received my Ph.D. in Electrical and Computer Engineering from the University of Maryland, College Park.

2022

Selected as a Rising Star in EECS.

2021

Direct Extraction of Signal and Noise Correlations from Two-Photon Calcium Imaging of Ensemble Neuronal Activity published in eLife.

2020

Multitaper Analysis of Semi-Stationary Spectra From Multivariate Neuronal Spiking Observations published in IEEE Transactions on Signal Processing.

2018

Received the Outstanding Teaching Assistant Award, Department of Electrical & Computer Engineering, University of Maryland.

2017

Received the Clark School of Engineering Distinguished Graduate Fellowship, University of Maryland.

2016

Received multiple prizes at the General Convocation, University of Peradeniya, Sri Lanka, including the Best Performance in Engineering, Best Performance in Electrical & Electronic Engineering, Best Performance in Engineering Mathematics, Best Performance in Electronic Communications, and Best Performance in Electrical Power and Machines.

2011

Received Most Outstanding Performance of the Year at Mahamaya Girls’ College, Kandy, Sri Lanka; ranked 4th in Sri Lanka in the G.C.E. Advanced Level Examination, Physical Science stream; and ranked 9th in Sri Lanka in the Olympiad Mathematics Competition.

Contact

Email: ar0621@princeton.edu
LinkedIn: Anuththara Rupasinghe
Google Scholar: Google Scholar Profile
GitHub: Anuththara-Rupasinghe