Berkant Turan

I am a second-year PhD candidate at the Institute of Mathematics, TU Berlin and a research associate at Zuse Institute Berlin (ZIB). Under the supervision of Prof. Sebastian Pokutta, I am currently part of the Interactive Optimization and Learning (IOL) research group at ZIB. Additionally, I am a member of the Berlin Mathematical School (BMS), which is part of the Math+ Excellence Cluster.

My current research focuses on the Interpretability of Deep Neural Networks. In particular, I am investigating the use of saliency maps created by feature selectors in a min-max game to gain valuable insights into the inner workings of black-box models.

Prior to joining IOL in 2022, I completed my Master’s thesis at the Fraunhofer Heinrich-Hertz Institute, where I worked on Deep Hybrid Discriminative-Generative Modeling. Specifically, I investigated the joint optimization of Variational Autoencoders (VAEs) and Residual Networks (ResNets) and analyzed the Out-of-Distribution detection behavior of these models in computer vision tasks.

selected publications

Interpretability Guarantees with Merlin-Arthur Classifiers

Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, and 1 more author

In International Conference on Artificial Intelligence and Statistics, 2024

Bib PDF

@inproceedings{waldchen2023formal,
  title = {Interpretability Guarantees with Merlin-Arthur Classifiers},
  author = {W{\"a}ldchen, Stephan and Sharma, Kartikey and Turan, Berkant and Zimmer, Max and Pokutta, Sebastian},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  year = {2024},
  organization = {PMLR},
}

Extending Merlin-Arthur Classifiers for Improved Interpretability

Berkant Turan

In Joint Proceedings of the xAI-2023 Late-breaking Work, Demos and Doctoral Consortium, co-located with the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023), Jul 2023

6-page extended abstract. Awarded Best Doctoral Proposal at xAI-2023.

Bib PDF

@inproceedings{TuranConsortium2023,
  title = {Extending Merlin-Arthur Classifiers for Improved Interpretability},
  author = {Turan, Berkant},
  booktitle = {Joint Proceedings of the xAI-2023 Late-breaking Work, Demos and Doctoral Consortium, co-located with the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023)},
  pages = {193-200},
  year = {2023},
  organization = {Springer},
  address = {Lisbon, Portugal},
  month = jul,
}

Robustness of Hybrid Discriminative-Generative Models

Berkant Turan

Technical University of Berlin, Jul 2022

MSc Thesis

Bib PDF Code

@mastersthesis{Turan2022Msc,
  title = {Robustness of Hybrid Discriminative-Generative Models},
  author = {Turan, Berkant},
  year = {2022},
  school = {Technical University of Berlin},
  type = {mastersthesis},
}

Modeling and Simulation of Convective Flows in the Outer Earth’s Core using the Finite Element Method

Berkant Turan

Technical University of Berlin, Jul 2018

BSc Thesis

Bib PDF Code

@bachelorsthesis{Turan2018Bsc,
  title = {Modeling and Simulation of Convective Flows in the Outer Earth's Core using the Finite Element Method},
  author = {Turan, Berkant},
  year = {2018},
  school = {Technical University of Berlin},
  type = {mastersthesis},
}