Vijay Sadashivaiah

I am a Computer Science PhD student at Rensselaer Polytechnic Institute advised by Professor James A. Hendler and Professor Chris R. Sims. My research interests lie in the area of human-inspired methods to advance artificial intelligence (AI) algorithms. Specifically, I am interested in exploring how the human brain abstracts away knowledge from one context and later uses it to learn quickly and efficiently in new contexts. This spans the areas of transfer learning, reinforcement learning, representation learning and deep learning. I am also interested in improving our understanding of machine learning methods through explainable/interpretable ML architectures.

Previously, I received my B.S. in Electrical Engineering at PES Institute of Technology and M.S. in Biomedical Engineering at Johns Hopkins University. I have been advised by such wonderful advisors: Professor Sridevi Sarma at JHU, Dr. Qiang Chen and Dr. Kristen Maynard at LIBD, Professor Carl Petersen at EPFL, and Professor Achuta Kadambi at MIT.

Email  /  CV  /  Google Scholar  /  Twitter  /  LinkedIn  /  GitHub


PontTuset Auto-Transfer: Learning to Route Transferrable Representations
Keerthiram Murugesan*, Vijay Sadashivaiah*, Ronny Luss, Karthikeyan Shanmugam, Pin-Yu Chen, Amit Dhurandhar (* equal contribution)
ICLR 2022
arXiv / code

We introduce multi-armed bandit based representation routing to improve transfer learning in computer vision tasks.

PontTuset Single-nucleus transcriptome analysis reveals cell-type-specific molecular signatures across reward circuitry in the human brain
Matthew N Tran, Kristen R Maynard, Abby Spangler, Louise A Huuki, Kelsey D Montgomery, Vijay Sadashivaiah, Madhavi Tippani, Brianna K Barry, Dana B Hancock, Stephanie C Hicks, Joel E Kleinman, Thomas M Hyde, Leonardo Collado-Torres, Andrew E Jaffe, Keri Martinowich
Neuron 2021
paper / code

A single-nucleus RNA-sequencing resource of 70,615 high-quality nuclei to generate a molecular taxonomy of cell types across five human brain regions.

PontTuset SUFI: An automated approach to spectral unmixing of fluorescent multiplex images captured in mouse and postmortem human brain tissues
Vijay Sadashivaiah, Madhavi Tippani, Stephanie C Page, Sang Ho Kwon, Svitlana V Bach, Rahul A Bharadwaj, Thomas M Hyde, Joel E Kleinman, Andrew E Jaffe, Kristen R Maynard,
bioRxiv 2021
bioRxiv / code

An automated approach to spectral unmixing of fluorescent images

PontTuset KCNH2-3.1 mediates aberrant complement activation and impaired hippocampal-medial prefrontal circuitry associated with working memory deficits
Ming Ren, Zhonghua Hu, Dr. Qiang Chen, Andrew E Jaffe, Yingbo Li, Vijay Sadashivaiah, Shujuan Zhu, Nina Rajpurohit, Joo Heon Shin, Wei Xia, Yankai Jia, Jingxian Wu, Sunny Lang Qin, Xinjian Li, Jian Zhu, Qingjun Tian, Daniel Paredes, Fengyu Zhang, Kuan Hong Wang, Venkata S Mattay, Joseph H Callicott, Karen F Berman, Daniel R Weinberger, Feng Yang
Molecular Psychiatry 2019

PontTuset Modeling the interactions between stimulation and physiologically induced APs in a mammalian nerve fiber: dependence on frequency and fiber diameter.
Vijay Sadashivaiah, Pierre Sacré, Yun Guan, William S Anderson, Sridevi V Sarma
Journal of Computational Neuroscience 2019, EMBC 2018, EMBC 2017
paper / related paper 1 / related paper 2 / related paper 3 / code

We constructed a mechanistic, stochastic and functional models of nerve fiber to quantify interactions.

PontTuset Voltage-sensitive dye imaging of mouse neocortex during a whisker detection task
Alexandros Kyriakatos, Vijay Sadashivaiah, Yifei Zhang, Alessandro Motta, Mattieu Auffret, Carl CH Petersen
Neurophotonics 2017

We studied the sensory motor interactions in mice brain using voltage sensitive dye imaging.

Source code credit to Dr. Jon Barron