Can Gümeli
PhD Candidate
Garching bei München, Bavaria, Germany
Summary
👤
Senior🎓
Top SchoolCan Gümeli is a PhD candidate in visual computing at TU Munich with 11 years of hands-on experience in deep learning and 3D computer vision, focused on understanding the world through object semantics. He combines academic rigor—top grades in his MSc and an ongoing doctoral project—with industry exposure from a Snap research internship and work on high-performance quantum simulation at Intel. An active contributor to open-source ML tooling, he improved batch normalization APIs and tests in the Knet.jl deep learning framework, demonstrating care for low-level numeric correctness across data types and dimensions. Comfortable teaching and mentoring, he has supported deep learning coursework while producing research that bridges theory and real-world perception problems. Based in Garching near Munich, he brings a pragmatic research mindset that repeatedly moves ideas from prototype code to robust implementations.
11 years of coding experience
Computer Engineering, 3.66/4.0, Computer Engineering, 3.66/4.0 at Koç ÜniversitesiMaster of Science, Computer Science, Cumulative: 1.4/1.0, Master Thesis: 1.0/1.0, Master of Science, Computer Science, Cumulative: 1.4/1.0, Master Thesis: 1.0/1.0 at Technische Universität München
Github Skills (8)
neural-network10
machine-learning10
deep-learning10
batch-normalization10
knexjs10
knn10
data-science10
julia10
Programming languages (3)
Github contributions (5)
denizyuret/Knet.jl
Nov 2017 - Feb 2018
Koç University deep learning framework.
Role in this project:
ML Engineer
ML EngineerContributions:36 commits, 13 PRs, 38 comments in 2 months
Contributions summary:Can made several API changes and implemented new features related to batch normalization within the Knet.jl deep learning framework. They modified the `batchnorm` API and added new tests for various dimensions and data types. Additionally, the user updated example code to use the modified batchnorm functionality.
data-sciencedeep-learningknetneural-networksmachine-learning
cangumeli/ROCA
Mar 2022 - Nov 2022
Contributions:28 commits, 28 pushes, 4 branches in 8 months
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.