E-mail: urszula.markowska-kaczmar@pwr.edu.pl

Unit: Faculty of Information and Communication Technology (N) » Departament of Artificial intelligence

pl. Grunwaldzki 9, 50-377 Wrocław
building D-2, room 201/18
phone +48 71 320 2466

Office hours

• Monday 6.30 – 7.30
• Tuesday 15.00 - 17.00
• Wednesday 11.15-12.15

---

Research fields

• deep learning; machine learning; neural networks; various applications of intelligent methods.

---

Recent papers

2015

• Markowska-Kaczmar U., Kołdowski M., Spiking neural network vs multilayer perceptron: who is the winner in the racing car computer game. Soft Computing. 2015, vol. 19, nr 12, pp. 3465-3478.

2014

• Kamola G., Spytkowski M., Paradowski M.T., Markowska-Kaczmar U., Image-based logical document structure recognition. Pattern Analysis and Applications. 2014, vol. 17, nr 3, pp. 1-15.

2012

• Sas J., Markowska-Kaczmar U., Similarity-based training set acquisition for continuous handwriting recognition. Information Sciences. 2012, vol. 191, pp. 226-244.

2011

• Kwaśnicka H., Markowska-Kaczmar U., Mikosik M., Flocking behaviour in simple ecosystems as a result of artificial evolution. Applied Soft Computing. 2011, vol. 11, nr 1, pp. 982-990.

2005

• Markowska-Kaczmar U., Trelak W., Fuzzy logic and evolutionary algorithm - two techniques in rule extraction from neural networks, Neurocomputing 2005 vol. 63 pp. 359-379

Papers in DONA database

Homepage

---

Selected publications
1	Article 2025 Michał Karolewski, Michał Wawrzyniak, Karol Szymończyk, Joanna I Szołomicka, Jakub Pyka, Karol Kulawiec, Aneta Demidaś, Masticatory organ dysfunction recognition based on multimodal information. Engineering Applications of Artificial Intelligence. 2025, vol. 144, art. 109998, s. 1-20. ISSN: 0952-1976; 1873-6769 Resources:DOIURLSFX
2	Proceeding paper 2024 Filip Strzałka, Gradient Overdrive: aviding negative randomness effects in Stochastic Gradient Descent. W: Recent Challenges in Intelligent Information and Database Systems : 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Ras Al Khaimah, UAE, April 15–18, 2024 : proceedings. Pt. 1 / eds. Ngoc Thanh Nguyen [i in.]. Singapore : Springer, cop. 2024. s. 175-186. ISBN: 978-981-97-5936-1; 978-981-97-5937-8 Resources:DOIURLSFX
3	Article 2024 Michał P Karol, Łukasz Fuławka, Deep learning for cancer cell detection: do we need dedicated models?. Artificial Intelligence Review. 2024, vol. 57, art. 53, s. 1-36. ISSN: 0269-2821; 1573-7462 Resources:DOIURLSFX
4	Monographs and other books editing 2023 Nikhil Jain, Chee Peng Lim, Lakhmi C Jain, Advances in smart healthcare paradigms and applications : outstanding women in healthcare. Vol. 1. Cham: Springer, cop. 2023. XII, 255 s. ISBN: 978-3-031-37305-3; 978-3-031-37306-0 (Intelligent Systems Reference Library, ISSN 1868-4394; vol. 244) Resources:DOI
5	Monograph chapter 2023 Joanna I Szołomicka, An overview of few-shot learning methods in analysis of histopathological images. W: Advances in smart healthcare paradigms and applications : outstanding women in healthcare. Vol. 1 / eds. Halina Kwaśnicka [i in.]. Cham : Springer, cop. 2023. s. 87-113. ISBN: 978-3-031-37305-3; 978-3-031-37306-0 Resources:DOISFX
6	Article 2022 Sebastian Jamroziński, Semi‑supervised classifier guided by discriminator. Scientific Reports. 2022, vol. 12, art. 14665, s. 1-17. ISSN: 2045-2322 Resources:DOIURLSFX
7	Proceeding paper 2021 Daniel Popek, Utterance style transfer using deep models. W: Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 25th International Conference KES 2021 / eds. Jaroslaw Watrobski [i in.]. Amsterdam : Elsevier, cop. 2021. s. 2132-2141. Resources:DOISFX
8	Proceeding paper 2021 Adrian Ślimak, Creating herd behavior by virtual agents using neural networks. W: Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 25th International Conference KES 2021 / eds. Jaroslaw Watrobski [i in.]. Amsterdam : Elsevier, cop. 2021. s. 437-446. Resources:DOISFX
9	Article 2021 Michał Kosturek, Extreme learning machine versus classical feedforward network. Comparison from the usability perspective. Neural Computing & Applications. 2021, vol. 33, s. 15121-15144. ISSN: 0941-0643; 1433-3058 Resources:DOIURLSFX
10	Article 2021 Mateusz Zimoch, Human flow recognition using deep learning and image processing methods. Engineering Applications of Artificial Intelligence. 2021, vol. 104, art. 104346, s. 1-11. ISSN: 0952-1976; 1873-6769 Resources:DOISFX

All publications