Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Daggitt, Matthew L."'
Autor:
Casadio, Marco, Dinkar, Tanvi, Komendantskaya, Ekaterina, Arnaboldi, Luca, Daggitt, Matthew L., Isac, Omri, Katz, Guy, Rieser, Verena, Lemon, Oliver
Deep neural networks have exhibited substantial success in the field of Natural Language Processing and ensuring their safety and reliability is crucial: there are safety critical contexts where such models must be robust to variability or attack, an
Externí odkaz:
http://arxiv.org/abs/2403.10144
Recent work has described the presence of the embedding gap in neural network verification. On one side of the gap is a high-level specification about the network's behaviour, written by a domain expert in terms of the interpretable problem space. On
Externí odkaz:
http://arxiv.org/abs/2402.01353
Autor:
Daggitt, Matthew L., Kokke, Wen, Atkey, Robert, Slusarz, Natalia, Arnaboldi, Luca, Komendantskaya, Ekaterina
Neuro-symbolic programs -- programs containing both machine learning components and traditional symbolic code -- are becoming increasingly widespread. However, we believe that there is still a lack of a general methodology for verifying these program
Externí odkaz:
http://arxiv.org/abs/2401.06379
Autor:
Casadio, Marco, Arnaboldi, Luca, Daggitt, Matthew L., Isac, Omri, Dinkar, Tanvi, Kienitz, Daniel, Rieser, Verena, Komendantskaya, Ekaterina
Verification of machine learning models used in Natural Language Processing (NLP) is known to be a hard problem. In particular, many known neural network verification methods that work for computer vision and other numeric datasets do not work for NL
Externí odkaz:
http://arxiv.org/abs/2305.04003
Autor:
Ślusarz, Natalia, Komendantskaya, Ekaterina, Daggitt, Matthew L., Stewart, Robert, Stark, Kathrin
Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications are stated and an interpretation function that translates expressions
Externí odkaz:
http://arxiv.org/abs/2303.10650
The rising popularity of neural networks (NNs) in recent years and their increasing prevalence in real-world applications have drawn attention to the importance of their verification. While verification is known to be computationally difficult theore
Externí odkaz:
http://arxiv.org/abs/2207.06741
Autor:
Casadio, Marco, Komendantskaya, Ekaterina, Rieser, Verena, Daggitt, Matthew L., Kienitz, Daniel, Arnaboldi, Luca, Kokke, Wen
With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks notoriously present low robustness and can be highly sensitive to small in
Externí odkaz:
http://arxiv.org/abs/2206.14575
Verification of neural networks is currently a hot topic in automated theorem proving. Progress has been rapid and there are now a wide range of tools available that can verify properties of networks with hundreds of thousands of nodes. In theory thi
Externí odkaz:
http://arxiv.org/abs/2202.05207
In this paper we present new general convergence results about the behaviour of the Distributed Bellman-Ford (DBF) family of routing protocols, which includes distance-vector protocols (e.g. RIP) and path-vector protocols (e.g. BGP). Our results appl
Externí odkaz:
http://arxiv.org/abs/2106.01184
Verification of AI is a challenge that has engineering, algorithmic and programming language components. For example, AI planners are deployed to model actions of autonomous agents. They comprise a number of searching algorithms that, given a set of
Externí odkaz:
http://arxiv.org/abs/2105.11267