From networks to circuits: a structured approach to AI interpretability
Bianka S. Kowalska, Halina Kwaśnicka
Communications in computer and information science
2026
Profil
Bianka Kowalska
Doktorant
Wykształcenie
2017
inżynier informatyki
Politechnika Wrocławska
2019
magister informatyki
Politechnika Wrocławska
Publikacje(5)
Unboxing the black box: a survey on mechanistic interpretability for algorithmic understanding of neural networks
Bianka S. Kowalska, Halina Kwaśnicka
Machine Learning 2026 vol. 115, art. 190, s. 1-41.
2026
Building a dataset of Wrocław’s historic tenements
Aleksandra S. Marcinów, Małgorzata Biegańska, Bianka S Kowalska, Hubert Baran, Daniil Hardzetski, Halina Kwaśnicka
Image annotation for machine learning applications. Architectus 2024 nr 3, s. 55-64.
2024
Analysis of the new architectural dataset NeoFaçade and its potential in machine learning
Bianka S. Kowalska, Hubert Baran, Daniil Hardzetski, Halina Kwaśnicka, Aleksandra S Marcinów, Małgorzata Biegańska
Architectus
2024
Development of low-cost high-frequency data acquisition system for energy harvesting applications
Rafał P. Mech, Przemysław K Wiewiórski, Bianka S Kowalska, Oleksandr Ivanow
Millersville, PA : Materials Research Forum LLC, cop. 2023. s. 83-90.
2022