Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Mohr, Stefanie"'
Autor:
Azeem, Muqsit, Grobelna, Marta, Kanav, Sudeep, Kretinsky, Jan, Mohr, Stefanie, Rieder, Sabine
The behavior of neural networks (NNs) on previously unseen types of data (out-of-distribution or OOD) is typically unpredictable. This can be dangerous if the network's output is used for decision-making in a safety-critical system. Hence, detecting
Externí odkaz:
http://arxiv.org/abs/2405.10350
Strategies for partially observable Markov decision processes (POMDP) typically require memory. One way to represent this memory is via automata. We present a method to learn an automaton representation of a strategy using a modification of the L*-al
Externí odkaz:
http://arxiv.org/abs/2401.07656
Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that is similar
Externí odkaz:
http://arxiv.org/abs/2307.10891
While abstraction is a classic tool of verification to scale it up, it is not used very often for verifying neural networks. However, it can help with the still open task of scaling existing algorithms to state-of-the-art network architectures. We in
Externí odkaz:
http://arxiv.org/abs/2006.13735