Kirill Bykov

Machine Learning PhD Student, Explainable AI


Google Scholar


GitHub Profile

About me

I am a Machine Learning PhD student at the TU Berlin and ATB Potsdam, working on Explainable AI under the supervision of Marina HΓΆhne and Klaus-Robert MΓΌller. I am working at Understandable Machine Intelligence lab and I am part of BIFOLD graduate school. My work is mainly focused on global Explainable AI methods – I develop methods so that we can comprehend what abstractions and concepts Deep Neural Networks learn, what is the purpose and function of individual neurons within the networks, as well as how these neurons pass information to each other, forming more complex circuits.



manipulating-publish.svg Paper | Code | Twitter Thread

invert-publish.svg Paper | Code | Twitter Thread

diversity-publish.svg Paper | Twitter Thread

fsca-publish.svg Paper

dora-publish.svg Paper | Code | Video

watermarks-publish.svg Paper | Code | Twitter Thread

noisegrad-publish.svg Paper | Code | Twitter Thread | Newspaper Article (DE)