Close

Vivek Sivaraman Narayanaswamy


ML/AI Researcher - Ph.D. Student - Arizona State University

Download Resume

About Me

Hello all! Welcome to my website! I am Vivek, a PhD student focusing on Machine Learning/AI research with a strong publication record (Neurips, ICML, AAAI, Interspeech, ICASSP) and experience with problem solving in computer vision, speech/audio and healthcare AI.

I am advised by Dr. Andreas Spanias at Arizona State University. I am also closely advised, mentored and guided by Dr. Jayaraman J. Thiagarajan from Lawrence Livermore National Labs for my research.

While maintaining a consistent academic record, I have also had the opportunity to work as a research intern at LLNL for three consecutive summers ('19, '20 and '21) as well as with Qualcomm R&D ('18).
I am very keen on researching and identifying critical problems in the field of machine learning and how to build AI tools that can be safely yet reliably deployed.

My core research topics include but not limited to: Deep learning, supervised learning, unsupervised learning, generative modeling, inverse problems, uncertainty quantification, explainable AI, out-of-distribution detection.

News

  • Paper titled 'Improved Medical Out-of-Distribution Detectors For Modality and Semantic Shifts' accepted at ICML Principles of Distribution Shifts Workshop (PODS 22). Link
  • Paper titled 'Using Direct Error Predictors to Improve Model Safety and Interpretability' accepted at ICML Interpretable Machine Learning for Healthcare Workshop (IMLH 22). Link

Experience

Lawrence Livermore National Laboratory

Computing Scholar Intern

Research and software development on designing neural network based surrogates for scientific simulators.
Preparing a manuscript with the research findings to be submitted to Nature Comm. 2022.

Lawrence Livermore National Laboratory

Computing Scholar Intern

Developed novel algorithms and software to analyze and accurately explain predictions of black-box classification models. The proposed approach produces high fidelity explanations robust to data-domain shifts.
Published the research findings at AAAI, 2020.

Lawrence Livermore National Laboratory

Computing Scholar Intern

Developed novel training strategies to solve ill-posed inverse problems under limited data scenarios (history matching) for scientific simulators.
Published the research findings at Neurips – ML for Physical Sciences Workshop, 2019.

Qualcomm R&D

Interim Engineering Intern

Developed python software libraries for automating Wi-Fi testing, integration, post processing and data visualization.
Assisted managers and project leads in the process of wireless testing in different practical deployments.

Arizona State University

Graduate Research Associate

Research and software development on computer vision, speech/audio and scientfic data using deep learning.
Collaborating with NXP Semiconductors for research on sensor calibration with machine learning.
Actively participated in the NSF Photovoltaic Cyber Physical System project and published 4+ conference papers and book chapters.

Education

Arizona State University

August 2017 - Present

Ph.D. in Electrical Engineering

Courses: Digital Signal Processing, Communication Systems, Random Signal Theory, Detection and Estimation Theory, Adaptive Signal Processing, Speech Processing and Audio Perception, Statistical Machine Learning, Convex Optimization, Artificial Neural Computation.

Anna University, India

June 2013 - May 2017

Bachelor of Engineering in Electronics and Communication Engineering

Publications

Improved Medical Out-of-Distribution Detectors For Modality and Semantic Shifts

V. Narayanaswamy, Y.Mubarka, R. Anirudh, D. Rajan, A. Spanias, J. J. Thiagarajan, ICML2022 Principles of Distribution Shifts Workshop

Link

Using Direct Error Predictors to Improve Model Safety and Interpretability

V. Narayanaswamy, D. Rajan, A. Spanias, J. J. Thiagarajan, ICML2022 Principles of Distribution Shifts Workshop

Link

Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images

V. Narayanaswamy, R. Subramayam, M. Naufel, A. Spanias, J. J. Thiagarajan, ICML 2022

Link

Designing Counterfactual Generators using Deep Model Inversion

J. J. Thiagarajan, V. Narayanaswamy, D. Rajan, J. Liang, A. Chaudhary, A. Spanias, Neurips 2021

Link

Accurate and Robust Feature Importance Estimation Under Distribution Shifts

J. J. Thiagarajan, V. Narayanaswamy, R. Anirudh, P. Bremer, AAAI 2021

Link

On the Design of Deep Priors for Unsupervised Audio Restoration

V. Narayanaswamy, J. J. Thiagarajan, A. Spanias, Interspeech 2021

Link

Using Deep Image Priors to Generate Counterfactual Explanations

V. Narayanaswamy, J. J. Thiagarajan, A. Spanias, ICASSP 2021

Link

Unsupervised Audio Source Separation using Generative Priors

V. Narayanaswamy, J. J. Thiagarajan, R. Anirudh, A. Spanias, Interspeech 2020

Link

Selected publications are listed above. For the complete list of publications, visit my Google Scholar!

Skills

Get in Touch


Email ID: vnaray29@asu.edu