Arber Zela
Postdoctoral Researcher at EPFL
Lausanne, Vaud, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolArber Zela is a postdoctoral researcher and AutoML specialist with a decade of experience focused on Automated Deep Learning, particularly Neural Architecture Search and hyperparameter optimization. He completed a PhD at the University of Freiburg and has held research positions at ELLIS, Oxford, Samsung, and now EPFL, blending academic rigor with industry-facing internships. A hands-on contributor to NASLib, he expanded the library with DARTS and NAS-Bench-1Shot1 search spaces and implemented mixed operation and cell structures, making NAS research more accessible. Based in Freiburg, Germany, he combines deep theoretical knowledge with practical engineering—often surfacing reproducible, runnable examples—and has a background bridging electrical engineering and computer science that informs his systems-oriented approach.
10 years of coding experience
2 years of employment as a software developer
Doctor of Science, Computer Science, Doctor of Science, Computer Science at The University of FreiburgBachelor of Science - BS, Electrical and Electronics Engineering, Bachelor of Science - BS, Electrical and Electronics Engineering at Universiteti Politeknik i Tiranës
Github Skills (10)
pytorch10
machine-learning10
deep-learning10
python10
nas10
neural-architecture-search10
automl9
github9
lstm9
linear-algebra7
Programming languages (4)
Github contributions (5)
automl/NASLib
May 2019 - Jun 2022
NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 1 review, 272 commits in 3 years 1 month
Contributions summary:Arber's commits primarily focus on the development and integration of Neural Architecture Search (NAS) capabilities within the NASLib library. This includes adding new search spaces, specifically DARTS and NAS-Bench-1Shot1, which expands the library's functionality. The user implemented mixed operation and cell structures. Also, contributions include fixing bugs in existing code and providing runnable examples.
nasneural-architecture-searchautoml
arberzela/EfficientNAS
Jul 2018 - Feb 2020
Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906
Contributions:6 commits, 9 pushes, 2 branches in 1 year 7 months
deep-learninghyperparametersautomlimage-classificationneural-architecture-search
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.