3 citations · 3 across the 6 of their papers we have counts for
6 papers
The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
Eric Alsmann, Martin Lange, Marco Sälzer
We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs…
On the Expressiveness of State Space Models via Temporal Logics
Eric Alsmann, Lowejatan Noori, Martin Lange
We investigate the expressive power of state space models (SSM), which have recently emerged as a potential alternative to transformer architectures in large language models. Build…
The Computational Complexity of Satisfiability in State Space Models
Eric Alsmann, Martin Lange
We analyse the complexity of the satisfiability problem ssmSAT for State Space Models (SSM), which asks whether an input sequence can lead the model to an accepting configuration.…
Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning
Marco Sälzer, Eric Alsmann, Martin Lange
We analyse the complexity of the satisfiability problem, or similarly feasibility problem, (trSAT) for transformer encoders (TE), which naturally occurs in formal verification or i…
Verifying And Interpreting Neural Networks using Finite Automata
Marco Sälzer, Eric Alsmann, Florian Bruse +1
Verifying properties and interpreting the behaviour of deep neural networks (DNN) is an important task given their ubiquitous use in applications, including safety-critical ones, a…
Separating the Expressive Power of Propositional Dynamic and Modal Fixpoint Logics
Eric Alsmann, Florian Bruse, Martin Lange
We investigate the expressive power of the two main kinds of program logics for complex, non-regular program properties found in the literature: those extending propositional dynam…