Keshigeyan Chandrasegaran
PhD Candidate
Palo Alto, California, United States
Summary
👤
Senior🎓
Top SchoolKeshigeyan Chandrasegaran is a third-year Computer Science PhD candidate at Stanford University advised by Fei-Fei Li and Juan Carlos Niebles, focusing on computer vision and machine learning with eight years of industry and research experience. He has applied vision systems to real-time robotics and synthetic data pipelines in startup capstones, researched IoT and sentiment-driven financial models at SUTD, and contributed as a researcher at Liquid AI and Radical Numerics. Comfortable bridging academia and product, he has built end-to-end stacks from smart contracts to DApps and deployed ML prototypes in production-like settings. Based in Palo Alto, he combines rigorous research training with hands-on engineering, and his background in entrepreneurship programs and international study hints at a pragmatic, globally minded approach to turning ML research into deployable systems.
8 years of coding experience
6 years of employment as a software developer
Lean LaunchPad Programme SUTD, Entrepreneurship/Entrepreneurial Studies, Lean LaunchPad Programme SUTD, Entrepreneurship/Entrepreneurial Studies at National University of SingaporeBachelor of Engineering - BE Honours, Information Systems Technology and Design, Summa Cum Laude, Bachelor of Engineering - BE Honours, Information Systems Technology and Design, Summa Cum Laude at Singapore University of Technology and Design (SUTD)Summer University, Business Analytics, Summer University, Business Analytics at Technische Universität BerlinDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Stanford University
English, Tamil
Github Skills (44)
representations10
image-retrieval9
decay9
generative8
spectrum8
retrieval8
computer-vision7
resnet6
temperature6
deep-learning6
densenet6
mobilenet6
pytorch6
efficientnet5
smoothing5
Programming languages (3)
Github contributions (5)
sutd-visual-computing-group/Fourier-Discrepancies-CNN-Detection
Apr 2021 - Jun 2021
In this work, we show that high frequency Fourier spectrum decay discrepancies are not inherent characteristics for existing CNN-based generative models. (CVPR 2021)
Contributions:51 commits, 2 PRs, 11 pushes in 2 months
pytorchdeep-learningcharacteristicshigh-frequencyfourier
keshik6/KITTI-2d-object-detection
Apr 2019 - May 2019
Contributions:84 commits, 20 pushes, 1 branch in 21 days
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.