Artificial Intelligence Techniques E192-07
Our research aims at enabling machines to mimic human-like intelligence, via models and algorithms to process vast amounts of data, recognize patterns, and make decisions, using techniques from machine and deep learning as well as symbolic reasoning.
Contact
- Head: Thomas Lukasiewicz
- Web: informatics.tuwien.ac.at/orgs/e192-07
- Location: Erzherzog-Johann-Platz 1
On This Page
About
Our research aims at enabling machines to mimic human-like intelligence, via models and algorithms to process vast amounts of data, recognize patterns, and make decisions, using techniques from machine and deep learning as well as symbolic reasoning.
In our research activities, we cover all modalities, including natural language processing and computer vision. We focus especially on (i) explainable AI, (ii) deep learning with logical constraints for safe AI , (iii) hybrid model-based approaches to explainable, fair, and robust AI, (iv) general AI via predictive coding and active inference, and (v) intelligent applications, such as in healthcare and law.
The research Unit Artificial Intelligence Techniques is part of the Institute of Logic and Computation.
Professors
Thomas Lukasiewicz T. Lukasiewicz
Head of Research Unit
Univ.Prof. Dipl.-Inf. Dr.
Scientific Staff
Eleonora Giunchiglia E. Giunchiglia
PostDoc Researcher
PhD
Bayar Ilhan Menzat B. Menzat
PostDoc Researcher
PhD
Administrative Staff
Cemile Schmid C. Schmid
Office Services
Courses
2023W
- Probabilistic Reasoning / 192.030 / VU
- Project in Computer Science 1 / 192.021 / PR
- Project in Computer Science 2 / 192.022 / PR
- Scientific Research and Writing / 193.052 / SE
- Seminar for Master Students in Logic and Computation / 180.773 / SE
- Seminar in Artificial Intelligence: Machine Learning / 192.024 / SE
Projects
-
Explainable Artificial Intelligence in Healthcare
2023 – 2027 / AXA
Publications
- Rationalizing predictions by adversarial information calibration / Sha, L., Camburu, O.-M., & Lukasiewicz, T. (2023). Rationalizing predictions by adversarial information calibration. Artificial Intelligence, 315, 103828. https://doi.org/https://doi.org/10.1016/j.artint.2022.103828
- NoiER: An Approach for Training more Reliable Fine-Tuned Downstream Task Models / Jang, M., & Thomas Lukasiewicz. (2022). NoiER: An Approach for Training more Reliable Fine-Tuned Downstream Task Models. IEEE/ACM Transactions on Audio, Speech and Language Processing, 30, 2514–2525. https://doi.org/10.1109/TASLP.2022.3193292
- (Non-)Convergence Results for Predictive Coding Networks / Frieder, S., & Lukasiewicz, T. (2022). (Non-)Convergence Results for Predictive Coding Networks. In Proceedings of the 39th International Conference on Machine Learning (pp. 6793–6810). http://hdl.handle.net/20.500.12708/187543
Theses
-
Deep learning für das Semantic Web
/
Hohenecker, P. (2016). Deep learning für das Semantic Web [Diploma Thesis, Technische Universität Wien]. reposiTUm. https://doi.org/10.34726/hss.2016.37489
Download: PDF (1.11 MB)
And more…
Soon, this page will include additional information such as reference projects, conferences, events, and other research activities.
Until then, please visit Artificial Intelligence Techniques’ research profile in TISS .