December 2022: Robert Peharz held a tutorial at NeurIPS
Probabilistic Circuits: Representations, Inference, Learning and Applications
and a workshop about Neuro Causal and Symbolic AI as well.

December 2022:  "Probabilistic models based on continuous latent spaces, such as variational autoencoders, can be understood as uncountable mixture models where components depend continuously on the latent code."

Alvaro H.C. Correia, Gennaro Gala, Erik Quaeghebeur, Cassio de Campos, Robert Peharz
Continuous Mixtures of Tractable Probabilistic Models

arXiv link to accepted paper

November 2022:  "Causal models are powerful reasoning tools, but usually we don't know which model is the correct one. Traditionally, one first aims to find the correct causal model from data, which is then used for causal reasoning", states Robert Peharz.

Christian Toth, Lars Lorch, Christian Knoll, Andreas Krause, Franz Pernkopf, Robert Peharz, Julius Von Kügelgen - Active Bayesian Causal Inference

link to NeurIPS paper
more detailed tweeted Information

March 2022: Stealthy bit-flip attacks are menacing deep neural network applications. Our novel defence make the attacker's life much harder. Developed in the Dependable-Systems-Lab of the SiliconAustriaLabs.

Ozan Özdenizci and Robert Legenstein
Improving robustness against stealthy weight bit-flip attacks by output code matching. In
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022. (Link to PDF)

See the featured interview at CVPR Daily.

June 2021: Want to train sparsely connected neural network which is robust to adversarial attacks? Use our novel method developed in the Dependable-Systems-Lab of the SiliconAustriaLabs

Ozan Özdenizci and Robert Legenstein.
Training adversarially robust sparse networks via Bayesian connectivity sampling. In
Proceedings of the 38th International Conference on Machine Learning, Marina Meila and Tong Zhang, editors, volume 139 of
Proceedings of Machine Learning Research, pages 8314-8324. PMLR, 18-24 Jul 2021. (Link to PDF)

Congratulations Ozan.

June 2021: How to control a robotic elephant trunk with a Spiking Neural Network

Manuel Traub, Robert Legenstein, and Sebastian Otte.
Many-joint robot arm control with recurrent spiking neural networks. In
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021. accepted for publication. (Link to ArXiv PDF)

See the news features:

Our article on biologically plausible backprop through time "A solution to the learning dilemma for recurrent networks of spiking neurons" is featured in Nature Communication Editor's Highlights:

https://www.nature.com/collections/ceiajcdbeb

Oct 2020: The EU FET-Open project ADOPD (Adaptive Optical Dendrites) has started. See Projects.

In media (German):
https://www.derstandard.at/story/2000120886799/neue-zukunftstechnologien-tu-graz-startet-drei-visionaere-projekte

Aug 2020: The IGI team has published a new article in Nature Communications: A solution to the learning dilemma for recurrent networks of spiking neurons

read more...

June 2020: How do neurons in the brain interact to create the mind? IGI researchers tackled this question in a series of papers in PNAS, CerebralCortex, eNeuro. Read more...
 

May 2020: Nature Machine Intelligence published this News & Views article on our research: An alternative to backpropagation through time.

Mar 2020: The EU FET-Proactive project SMALL (Spiking Memristive Architectures for Learning to Learn) has started. See Projects and the Webpage.

Feb 2020: Don't miss these interviews with Wolfgang Maass on computational neuroscience, brain-inspired computation, and more at

Jan. 2020: On 10th of January, a cooperation between TU Graz and the Silicon Austria Labs has been started with a press conference and official signatures under a contract that establishes two joint research labs. The goal of the cooperation is to foster basic research for future microelectronics. The Institute of Theoretical Computer Science is part of the Depenendable Embedded Systems Lab, where research will focus on more reliable AI systems. Press release