1 code implementation • 25 Jan 2024 • Haoze Wu, Omri Isac, Aleksandar Zeljić, Teruhiro Tagomori, Matthew Daggitt, Wen Kokke, Idan Refaeli, Guy Amir, Kyle Julian, Shahaf Bassan, Pei Huang, Ori Lahav, Min Wu, Min Zhang, Ekaterina Komendantskaya, Guy Katz, Clark Barrett
This paper serves as a comprehensive system description of version 2. 0 of the Marabou framework for formal analysis of neural networks.
1 code implementation • 24 Jan 2024 • Matthew L. Daggitt, Wen Kokke, Robert Atkey
Recent work has described the presence of the embedding gap in neural network verification.
1 code implementation • 12 Jan 2024 • Matthew L. Daggitt, Wen Kokke, Robert Atkey, Natalia Slusarz, Luca Arnaboldi, Ekaterina Komendantskaya
Neuro-symbolic programs -- programs containing both machine learning components and traditional symbolic code -- are becoming increasingly widespread.
no code implementations • 21 Jun 2022 • Marco Casadio, Ekaterina Komendantskaya, Verena Rieser, Matthew L. Daggitt, Daniel Kienitz, Luca Arnaboldi, Wen Kokke
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 input perturbations.
no code implementations • 10 Feb 2022 • Matthew L. Daggitt, Wen Kokke, Robert Atkey, Luca Arnaboldi, Ekaterina Komendantskya
However, although work has managed to incorporate the results of these verifiers to prove larger properties of individual systems, there is currently no general methodology for bridging the gap between verifiers and interactive theorem provers (ITPs).
no code implementations • 29 Sep 2021 • Marco Casadio, Matthew L Daggitt, Ekaterina Komendantskaya, Wen Kokke, Robert Stewart
We also perform experiments to compare the applicability and efficacy of different training methods for ensuring the network obeys these different definitions.
1 code implementation • 3 Apr 2021 • Marco Casadio, Ekaterina Komendantskaya, Matthew L. Daggitt, Wen Kokke, Guy Katz, Guy Amir, Idan Refaeli
Neural networks are very successful at detecting patterns in noisy data, and have become the technology of choice in many fields.
3 code implementations • 24 May 2020 • Robert Griesemer, Raymond Hu, Wen Kokke, Julien Lange, Ian Lance Taylor, Bernardo Toninho, Philip Wadler, Nobuko Yoshida
We describe a design for generics in Go inspired by previous work on Featherweight Java by Igarashi, Pierce, and Wadler.
Programming Languages Logic in Computer Science
no code implementations • 3 Sep 2017 • Wen Kokke
And finally, we will put our system to use in the analysis of a simple example sentence.