|
Name and surname:
|
Mgr. Štefan Pócoš, PhD.
|
|
Document type:
|
Research/art/teacher profile of a person
|
|
The name of the university:
|
Comenius University Bratislava
|
|
The seat of the university:
|
Šafárikovo námestie 6, 818 06 Bratislava
|
| III.a - Occupation-position | III.b - Institution | III.c - Duration |
|---|---|---|
| Postdoctoral researcher | Comenius University Bratislava | 2024 - 2025 |
| V.5.a - Name of the course | V.5.b - Study programme | V.5.c - Degree | V.5.d - Field of study |
|---|---|---|---|
| Introduction to artificial intelligence | Applied informatics | 1 | Informatics |
| Neural networks | Applied informatics | 2 | Informatics |
Pócoš, Š., Bečková, I., and Farkaš, I. (2024). RecViT: Enhancing vision transformer with top-down information flow. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, pages 749–756. INSTICC, SciTePress.
Krakovská, A., Pócoš, Š., Mojžišová, K., Bečková, I., and Gubáš, J. X. (2022). State space reconstruction techniques and the accuracy of prediction. Communications in Nonlinear Science and Numerical Simulation, 111:106422.
Pócoš, Š., Bečková, I., and Farkaš, I. (2022). Examining the proximity of adversarial examples to class manifolds in deep networks. In Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., and Aydin, M., editors, Artificial Neural Networks and Machine Learning – ICANN 2022, pages 645–656, Cham. Springer Nature Switzerland.
Bečková, I., Pócoš Š., and Farkaš, I. (2020). Computational analysis of robustness in neural network classifiers. In Farkaš, I., Masulli, P., and Wermter, S., editors, Artificial Neural Networks and Machine Learning – ICANN 2020, pages 65–76, Cham. Springer International Publishing.
Pócoš, Š., Bečková, I., Kuzma, T., and Farkaš, I. (2021). Assessment of manifold unfolding in trained deep neural network classifiers. In Heintz, F., Milano, M., and O’Sullivan, B., editors, Trustworthy AI - Integrating Learning, Optimization and Reasoning, pages 93–103, Cham. Springer International Publishing.
Pócoš, Š., Bečková, I., and Farkaš, I. (2024). RecViT: Enhancing vision transformer with top-down information flow. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, pages 749–756. INSTICC, SciTePress.
Krakovská, A., Pócoš, Š., Mojžišová, K., Bečková, I., and Gubáš, J. X. (2022). State space reconstruction techniques and the accuracy of prediction. Communications in Nonlinear Science and Numerical Simulation, 111:106422.
Pócoš, Š., Bečková, I., and Farkaš, I. (2022). Examining the proximity of adversarial examples to class manifolds in deep networks. In Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., and Aydin, M., editors, Artificial Neural Networks and Machine Learning – ICANN 2022, pages 645–656, Cham. Springer Nature Switzerland.
Bečková, I., Pócoš Š., and Farkaš, I. (2020). Computational analysis of robustness in neural network classifiers. In Farkaš, I., Masulli, P., and Wermter, S., editors, Artificial Neural Networks and Machine Learning – ICANN 2020, pages 65–76, Cham. Springer International Publishing.
Pócoš, Š., Bečková, I., Kuzma, T., and Farkaš, I. (2021). Assessment of manifold unfolding in trained deep neural network classifiers. In Heintz, F., Milano, M., and O’Sullivan, B., editors, Trustworthy AI - Integrating Learning, Optimization and Reasoning, pages 93–103, Cham. Springer International Publishing.
Ebid, S. E., El-Tantawy, S., Shawky, D., & Abdel-Malek, H. L. (2025). Correlation-based pruning algorithm with weight compensation for feedforward neural networks. Neural Computing and Applications, 1-17.
Xu, L., & Wang, D. (2024). The reconstruction of equivalent underlying model based on direct causality for multivariate time series. PeerJ Computer Science, 10, e1922.
Zhang, Y., Wang, Z., Jiang, J., You, H., & Chen, J. (2022, October). Toward improving the robustness of deep learning models via model transformation. In Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering (pp. 1-13).
Jiang, J., Yang, J., Zhang, Y., Wang, Z., You, H., & Chen, J. (2024). A post-training framework for improving the performance of deep learning models via model transformation. ACM Transactions on Software Engineering and Methodology, 33(3), 1-41.
Del Tatto, V., Fortunato, G., Bueti, D., & Laio, A. (2024). Robust inference of causality in high-dimensional dynamical processes from the information imbalance of distance ranks. Proceedings of the National Academy of Sciences, 121(19), e2317256121.