Sharaj Panwar
Research Assistant at Texas A&M Engineering Experiment Station (TEES)
College Station, Texas, United States
Summary
👤
Senior🎓
Top SchoolSharaj Panwar is a research-driven machine learning engineer with nine years of experience applying deep learning to biomedical and signal-processing problems, currently a Research Assistant at Texas A&M’s TEES and a PhD candidate in Interdisciplinary Engineering. He has developed practical scientific ML solutions—transformer time-series models for glucose prediction, spatial VAEs that compress experimental signals while preserving key quantities, and uncertainty-aware physics-informed training using particle swarm optimization. Previously at UTSA he advanced EEG modeling with novel WGAN variants and hybrid CNN–RNN architectures that improved cross-session RSVP classification and cognitive-state prediction. Equally comfortable with PyTorch, TensorFlow and MATLAB, he bridges theory and application by turning generative and probabilistic models into reproducible pipelines for noisy biosignals. An uncommon strength is his track record of reducing experimental data footprints without sacrificing task-relevant information, enabling cheaper and more informative experiments.
9 years of coding experience
7 years of employment as a software developer
University of Texas at San AntonioDoctor of Philosophy - PhD, Interdisciplinary Engineering, Doctor of Philosophy - PhD, Interdisciplinary Engineering at Texas A&M UniversityBachelor of Technology - BTech, Electrical and Electronics Engineering, Bachelor of Technology - BTech, Electrical and Electronics Engineering at Dr APJ Abdul Kalam Technical University, Lucknow, Uttar Pradesh (India)
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
predict9
ieee9
generative9
modeling8
generative-adversarial-network8
keras7
tensorflow5
deep-learning5
Programming languages (1)
Github contributions (5)
sharajpanwar/HRNN
Mar 2018 - Apr 2019
Contributions:32 commits, 4 pushes in 1 year 1 month
sharajpanwar/CC-WGAN-GP
Feb 2019 - Mar 2021
Repo: IEEE TNSRE Article "Modeling EEG data distribution with a Wasserstein Generative Adversarial Network (WGAN) to predict RSVP Events" - Keras implementation
Contributions:126 commits, 17 pushes, 1 comment in 2 years 1 month
adversarialpredicttensorflowrsvpieee
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.