Paweł Zawistowski

Paweł Zawistowski

Ph.d. in Computer Science, Assistant Professor at Warsaw University of Technology, Researcher in Machine Learning and Artificial Intelligence.

Publications

Journal Articles

Exploring the microstructure–property relationship in polymer foams using advanced statistical methods, machine learning and deep learning: A review

Published in Computational Materials Science, 2025

This review explores the application of advanced statistical methods, machine learning, and deep learning techniques for understanding microstructure-property relationships in polymer foams.

Recommended citation: Walicki, D., Zawistowski, P., & Ryszkowska, J. (2025). "Exploring the microstructure–property relationship in polymer foams using advanced statistical methods, machine learning and deep learning: A review." Computational Materials Science. 256, 1-14.
Download Paper

Ground truth based comparison of saliency maps algorithms

Published in Scientific Reports, 2023

Research article published in Scientific Reports comparing saliency map algorithms using ground truth based methodology.

Recommended citation: Szczepankiewicz, K., Popowicz, A., Charkiewicz, K., Nałęcz-Charkiewicz, K., Szczepankiewicz, M., Lasota, S., Zawistowski, P., & Radlak, K. (2023). "Ground truth based comparison of saliency maps algorithms." Scientific Reports, Article 13.
Download Paper

Deep Learning Optimization Tasks and Metaheuristic Methods

Published in Fundamenta Informaticae, 2019

Journal article on applying metaheuristic methods to deep learning optimization tasks.

Recommended citation: Biedrzycki, R., Zawistowski, P., & Twardowski, B. (2019). "Deep Learning Optimization Tasks and Metaheuristic Methods." Fundamenta Informaticae, 168, Article 2–4.
Download Paper

Conference Papers

Testing and Verification of the Deep Neural Networks Against Sparse Pixel Defects

Published in SAFECOMP 2022 Workshops - Lecture Notes in Computer Science, 2022

Conference paper on testing deep neural networks against sparse pixel defects published in SAFECOMP 2022 Workshops proceedings.

Recommended citation: Szczepankiewicz, M., Radlak, K., Szczepankiewicz, K., Popowicz, A., & Zawistowski, P. (2022). "Testing and Verification of the Deep Neural Networks Against Sparse Pixel Defects." W M. Trapp, E. Schoitsch, J. Guiochet, & F. Bitsch (Redaktorzy), Proceedings of the Computer Safety, Reliability, and Security. SAFECOMP 2022 Workshops.
Download Paper

Metric Learning for Session-Based Recommendations

Published in Advances in Information Retrieval, 43rd European Conference on IR Research, ECIR 2021, 2021

Conference paper on applying metric learning techniques to session-based recommendation systems.

Recommended citation: Twardowski, B., Zawistowski, P., & Zaborowski, S. (2021). "Metric Learning for Session-Based Recommendations." W D. Hiemstra, M.-F. Moens, J. Mothe, R. Perego, M. Potthast, & F. Sebastiani (Redaktorzy), Advances in Information Retrieval, 43rd European Conference on IR Research, ECIR 2021, Proceedings.
Download Paper

Deep Neuroevolution: Training Neural Networks Using a Matrix-Free Evolution Strategy

Published in Neural Information Processing, Part I, 2021

Conference paper on deep neuroevolution methods for training neural networks using matrix-free evolution strategies.

Recommended citation: Jagodziński, D., Neumann, Ł., & Zawistowski, P. (2021). "Deep Neuroevolution: Training Neural Networks Using a Matrix-Free Evolution Strategy." W T. Mantoro, M. Lee, M. A. Ayu, K. W. Wong, & A. N. Hidayanto (Redaktorzy), Neural Information Processing, Part I.
Download Paper

Automatic hyperparameter tuning in on-line learning: Classic Momentum and ADAM

Published in 2020 International Joint Conference on Neural Networks (IJCNN), 2020

Conference paper on automatic hyperparameter tuning methods for online learning algorithms, focusing on momentum and ADAM optimizers.

Recommended citation: Wawrzyński, P., Zawistowski, P., & Lepak, Ł. (2020). "Automatic hyperparameter tuning in on-line learning: Classic Momentum and ADAM." 2020 International Joint Conference on Neural Networks (IJCNN), 1–8.
Download Paper

Machine learning models for predicting customer decision in motor claims settlements

Published in Proceedings of SPIE: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 2019

Conference paper on applying machine learning models to predict customer decisions in motor insurance claims settlements.

Recommended citation: Nowak, R. M., Neumann, Ł., Franus, W., Dąmbski, M., Smółkowski, A., & Zawistowski, P. (2019). "Machine learning models for predicting customer decision in motor claims settlements." W R. Romaniuk & M. G. Linczuk (Redaktorzy), Proceedings of SPIE: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019.
Download Paper

Paraphrase generation and evaluation: a view from the trenches

Published in Proceedings of SPIE: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 2019

Conference paper presenting practical insights into paraphrase generation and evaluation methods.

Recommended citation: Franus, W., Twardowski, B., Zawistowski, P., & Nowak, R. M. (2019). "Paraphrase generation and evaluation: a view from the trenches." W R. Romaniuk & M. G. Linczuk (Redaktorzy), Proceedings of SPIE: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019.
Download Paper

Adversarial examples: A survey

Published in 2018 Baltic URSI Symposium (URSI), 2018

Conference paper providing a comprehensive survey of adversarial examples in machine learning.

Recommended citation: Zawistowski, P. (2018). "Adversarial examples: A survey." 2018 Baltic URSI Symposium (URSI), CFP18N89-ART, 295–298.
Download Paper