About me

I am a final year Ph.D. candidate at Heriot-Watt University, Edinburgh, under the supervision of Prof. Ekaterina Komendantskaya. I am part of the AISEC (AI Secure and Explainable by Construction) group.

My research interestes include differentiable logics, substructural logics (especially fuzzy logics), contraint-aware training of neural networks and neurosymbolic methods, formal methods for machine learning and interactive theorem proving .

Publications

Neurosymbolic Framework for Bias Correction in Convolutional Neural Networks
P. Padalkar, N. Ślusarz, E. Komendantskaya, G. Gupta
Theory and Practice of Logic Programming, 2024
Taming differentiable logics with Coq formalisation
R. Affeldt, A. Bruni, E. Komendantskaya, N. Ślusarz, K. Stark
ITP 2024
Vehicle: Bridging the embedding gap in the verification of neuro-symbolic programs
M. L. Daggitt, W. Kokke, R. Atkey, N. Ślusarz, L. Arnaboldi, E. Komendantskaya
LIPCS FSCD 2024 (Invited Talk)
Logic of differentiable logics: Towards a uniform semantics of DL
N. Ślusarz, E. Komendantskaya, M. L. Daggitt, R. Stewart, K. Stark
LPAR 2023
Differentiable logics for neural network training and verification
N. Ślusarz, E. Komendantskaya, M. L. Daggitt, R. Stewart
NSV FoMLAS 2022

Natalia Ślusarz

About me

I am a final year Ph.D. candidate at Heriot-Watt University, Edinburgh, under the supervision of Prof. Ekaterina Komendantskaya. I am part of the AISEC (AI Secure and Explainable by Construction) group.

My research interestes include differentiable logics, substructural logics (especially fuzzy logics), contraint-aware training of neural networks and neurosymbolic methods, formal methods for machine learning and interactive theorem proving .

Publications

“Science is not about building a body of known 'facts'. It is a method for asking awkward questions and subjecting them to a reality-check, thus avoiding the human tendency to believe whatever makes us feel good.” ― Terry Pratchett