Academic Profile

Bio

Raghavendra Selvan (Raghav) is currently an Assistant Professor at the University of Copenhagen, with joint responsibilities at the Machine Learning Section (Dept. of Computer Science), Kiehn Lab (Department of Neuroscience) and the Data Science Laboratory. He received his PhD in Medical Image Analysis (University of Copenhagen, 2018), his MSc degree in Communication Engineering in 2015 (Chalmers University, Sweden) and his Bachelor degree in Electronics and Communication Engineering degree in 2009 (BMS Institute of Technology, India). Raghavendra Selvan was born in Bangalore, India.

His current research interests are broadly pertaining Medical Image Analysis using Quantum Tensor Networks, Bayesian Machine Learning, Resource-efficient ML, Graph-neural networks, Approximate Inference and multi-object tracking theory.

News

  • 2021-10: Paper accepted to Journal of Ecological Informatics
  • 2021-09: Started a consultancy project with FaunaPhotonics
  • 2021-07: Paper accepted to Nature Scientific Reports
  • 2021-06: AI Chemy project funded as co-applicant; UCPH funding (3.4M DKK)
  • 2021-06: Paper published in Nature Communications; Collaboration with Kiehn Lab
  • 2021-05: Two short papers accepted to be presented at MIDL-2021 [1][2]
  • 2021-04: Started as Chair of Neuroimaging Research Pipelines workgroup as part of the OHBM Sustainability and environmental action special interest group.
  • 2021-03: Paper accepted to the Journal of Machine Learning for Biomedical Imaging
  • 2021-02: Paper accepted to the Journal of Ecological Informatics with press release
  • 2021-02: Paper accepted to IPMI-2021 with an oral presentation
  • 2020-11: Carbontracker receives media attention [0] [1] [2] [3] [4]

Research Projects

(Switching to first person :)

I am actively involved in a wide range of research projects as part of my roles at the Machine Learning section and Data Science Lab of University of Copenhagen. Brief descriptions of ongoing and completed projects are listed below.

Ongoing projects

  • Low Resource Machine Learning: Reducing the reliance on high quality labeled data and expensive hardware resources can globally democratise ML methods. Addressing one of these factors, we recently introduced tensor networks for medical image classification tasks that require less than 10% of GPU resources when compared to traditional deep learning models. We have also put out a tool – Carbontracker – to predict and track carbon footprint of developing deep learning models, in an effort to encourage research into energy-efficient models.

  • AIChemy: Generative Modelling of nanoparticles: Obtaining structures from scattering data for nanomolecules turns out to be an expensive and difficult task. This ongoing collaboration with Prof. Kirsten Jensen’s group we are explorting generating valid nanomolecular structures from x-ray scattering data using deep generative models with promising early results.

  • Locomotion analysis: In this collabortion with Kiehn Lab, my role has been to analyze videos of mice running on treadmills in order to extract speed, cadence and coordination statistics. The results from analyzing some 1000 videos have accentuated the role of specific interneurons in the spinal cord that influence locomotion.

  • Quantifying insect biodiversity: In this ongoing collaboration with FaunaPhotonics, we are attempting unsupervised clustering of insects based on optically recorded signals from field data. An initial attempt involved using a variational autoencoder that dynamically adjusts the tradeoff between reconstruction and regularisation terms.

  • Uncertainty Quantification: Medical image segmentation with well calibrated and meaningful uncertainty estimation can be more useful in clinical settings. For example, we present a probabilistic segmentation model that uses normalizing flows to improve the diversity of segmented samples.

Completed projects