I am a PhD candidate at IST Austria at the research group of Tom Henzinger. My research topics are Machine Learning, Formal Methods, and Robotics.

Publications

Neural circuit policies enabling auditable autonomy
Mathias Lechner, Ramin Hasani, Alexander Amini, Thomas A. Henzinger, Daniela Rus, and Radu Grosu
In Nature Machine Intelligence, 2020 ([Paper link])

Learning Long-Term Dependencies in Irregularly-Sampled Time Series
Mathias Lechner, Ramin Hasani
To appear in 2020 Conference on Neural Information Processing Systems (NeurIPS), 2020

The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, and Radu Grosu
In 2020 International Conference on Machine Learning (ICML), 2020

Learning Representations for binary classification without backpropagation
Mathias Lechner
In 2020 International Conference on Learning Representations (ICLR), 2020

An SMT Theory of Fixed-Point Arithmetic
Marek Baranowski, Shaobo He, Mathias Lechner, Thanh Son Nguyen, and Zvonimir Rakamaric
In 2020 International Joint Conference on Automated Reasoning (IJCAR), 2020

Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-To-End Robot Learning Scheme
Mathias Lechner, Ramin Hasani, Daniela Rus, and Radu Grosu
In 2020 International Conference on Robotics and Automation (ICRA), 2020

How Many Bits Does it Take to Quantize Your Neural Network?
Mirco Giacobbe, Thomas A. Henzinger, and Mathias Lechner
In 2020 International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS), 2020

Lagrangian Reachtubes: The Next Generation
Sophie Gruenbacher, Jacek Cyranka, Mathias Lechner, Md. Ariful Islam, Scott Smolka, and Radu Grosu
In 2020 IEEE Conference on Decision and Control (CDC), 2020

Response characterization for auditing cell dynamics in long short-term memory networks
Ramin Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, and Daniela Rus
In 2019 International Joint Conference on Neural Networks (IJCNN), 2019

Designing worm-inspired neural networks for interpretable robotic control
Mathias Lechner, Ramin Hasani, Manuel Zimmer, Thomas A. Henzinger, and Radu Grosu
In 2019 International Conference on Robotics and Automation (ICRA), 2019

Awards

Distinguished Young Alumnus-Award 2018 Faculty of Informatics at TU Wien

Competitions

First Place In F1TENTH - Autonomous Racing Grand Prix at IFAC 2020