Banner Banner

Kirill Bykov

Icon

Technische Universität Berlin
Understandable Machine Intelligence Lab (M Höhne)

Kirill Bykov BIFOLD researcher
© Bykov

Kirill Bykov

Doctoral Researcher

Kirill Bykov is currently pursuing his doctoral research in Machine Learning at the Technical University of Berlin (TU Berlin). He is a member of the Understandable Machine Intelligence lab, under the guidance of Prof. Dr. Marina Höhne. Prior to embarking on his doctoral journey, Kirill earned a Cum Laude Master’s degree in Computer Science Engineering from TU Berlin and TU Eindhoven, as part of EIT Digital double-degree program. His academic foundation was laid with a Bachelor’s degree in Applied Mathematics and Computer Science from Saint-Petersburg State University. Kirill’s research primarily focuses on Explainable AI. He has a particular interest in global explanation methods, mechanistic interpretability, and Bayesian Neural Networks. 

  • 2020 - Cum Laude MSc, Computer Science and Engineering (double degree TU Berlin and TU Eindhoven)
  • 2018 - EIT Digital Excellence scholarship recipient
  • 2018 - Prize winner of Skoltech statistical Learning Theory Olympiad
  • 2018 - Prize winner of HSE applied Mathematics and Computer Science Olympiad
  • 2018 - International data science olympiad (IDAO) finalist

  • Machine Learning
  • Explainable AI
  • Mechanistic interpretability
  • Bayesian Neural Networks

Dilyara Bareeva, Marina M.-C. Höhne, Alexander Warnecke, Lukas Pirch, Klaus-Robert Müller, Konrad Rieck, Kirill Bykov

MANIPULATING FEATURE VISUALIZATIONS WITH GRADIENT SLINGSHOTS

January 11, 2024
https://doi.org/10.48550/arXiv.2401.06122

Kirill Bykov, Laura Kopf, Shinichi Nakajima, Marius Kloft, Marina M.-C. Höhne

Labeling Neural Representations with Inverse Recognition

November 22, 2023
https://doi.org/10.48550/arXiv.2311.13594

Dennis Grinwald, Kirill Bykov, Shinichi Nakajima, Marina MC Höhne

Visualizing the Diversity of Representations Learned by Bayesian Neural Networks

November 10, 2023
https://openreview.net/pdf?id=ZSxvyWrX6k

Kirill Bykov, Mayukh Deb, Dennis Grinwald, Klaus-Robert Müller, Marina M.-C. Höhne

DORA: Exploring Outlier Representations in Deep Neural Networks

July 10, 2023
https://doi.org/10.48550/arXiv.2206.04530

News
Explainable AI| Feb 23, 2024

Call for XAI-Papers!

Two research groups associated with BIFOLD take part in the organization of the 2nd World Conference on Explainable Artificial Intelligence. Each group is hosting a special track and has already published a Call for Papers. Researchers are encouraged to submit their papers by March 5th, 2024.