Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Sutton, Oliver J."'
Autor:
Sutton, Oliver J., Zhou, Qinghua, Wang, Wei, Higham, Desmond J., Gorban, Alexander N., Bastounis, Alexander, Tyukin, Ivan Y.
We reveal new methods and the theoretical foundations of techniques for editing large language models. We also show how the new theory can be used to assess the editability of models and to expose their susceptibility to previously unknown malicious
Externí odkaz:
http://arxiv.org/abs/2406.12670
Autor:
Tyukin, Ivan Y., Tyukina, Tatiana, van Helden, Daniel, Zheng, Zedong, Mirkes, Evgeny M., Sutton, Oliver J., Zhou, Qinghua, Gorban, Alexander N., Allison, Penelope
We present a new methodology for handling AI errors by introducing weakly supervised AI error correctors with a priori performance guarantees. These AI correctors are auxiliary maps whose role is to moderate the decisions of some previously construct
Externí odkaz:
http://arxiv.org/abs/2402.00899
Publikováno v:
Artificial Neural Networks and Machine Learning ICANN 2023. Lecture Notes in Computer Science, vol 14254, pp 516-529. Springer, Cham
High dimensional data can have a surprising property: pairs of data points may be easily separated from each other, or even from arbitrary subsets, with high probability using just simple linear classifiers. However, this is more of a rule of thumb t
Externí odkaz:
http://arxiv.org/abs/2311.07579
Autor:
Sutton, Oliver J., Zhou, Qinghua, Tyukin, Ivan Y., Gorban, Alexander N., Bastounis, Alexander, Higham, Desmond J.
Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are robust to lar
Externí odkaz:
http://arxiv.org/abs/2309.03665
Autor:
Houston, Paul, Hubbard, Matthew E., Radley, Thomas J., Sutton, Oliver J., Widdowson, Richard S. J.
Publikováno v:
J. Sci. Comput. 100 (2024) 52
We introduce an $hp$-version discontinuous Galerkin finite element method (DGFEM) for the linear Boltzmann transport problem. A key feature of this new method is that, while offering arbitrary order convergence rates, it may be implemented in an almo
Externí odkaz:
http://arxiv.org/abs/2304.09592
We consider the problem of data classification where the training set consists of just a few data points. We explore this phenomenon mathematically and reveal key relationships between the geometry of an AI model's feature space, the structure of the
Externí odkaz:
http://arxiv.org/abs/2211.03607
Autor:
Tyukin, Ivan Y., Tyukina, Tatiana, van Helden, Daniël P., Zheng, Zedong, Mirkes, Evgeny M., Sutton, Oliver J., Zhou, Qinghua, Gorban, Alexander N., Allison, Penelope
Publikováno v:
In Information Sciences September 2024 678
We introduce a residual-based a posteriori error estimator for a novel $hp$-version interior penalty discontinuous Galerkin method for the biharmonic problem in two and three dimensions. We prove that the error estimate provides an upper bound and a
Externí odkaz:
http://arxiv.org/abs/2009.14140
We present a posteriori error estimates for inconsistent and non-hierarchical Galerkin methods for linear parabolic problems, allowing them to be used in conjunction with very general mesh modification for the first time. We treat schemes which are n
Externí odkaz:
http://arxiv.org/abs/2005.05661
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.