no code implementations • 15 Jan 2024 • Alexander Bork, Debraj Chakraborty, Kush Grover, Jan Kretinsky, Stefanie Mohr
Strategies for partially observable Markov decision processes (POMDP) typically require memory.
1 code implementation • 20 Jul 2023 • Calvin Chau, Jan Křetínský, Stefanie Mohr
In this work, we provide a more flexible framework where a neuron can be replaced with a linear combination of other neurons, improving the reduction.
no code implementations • 8 Oct 2021 • Stefanie Mohr, Konstantina Drainas, Juergen Geist
In this work, we present a selection of state-of-the-art Neural Networks (NN) for the prediction of water temperatures in six streams in Germany.
no code implementations • 24 Jun 2020 • Pranav Ashok, Vahid Hashemi, Jan Křetínský, Stefanie Mohr
While abstraction is a classic tool of verification to scale it up, it is not used very often for verifying neural networks.