Zobrazeno 1 - 10
of 636
pro vyhledávání: '"Gorban, A. N."'
Autor:
Sutton, Oliver J., Zhou, Qinghua, Wang, Wei, Higham, Desmond J., Gorban, Alexander N., Bastounis, Alexander, Tyukin, Ivan Y.
We reveal the theoretical foundations of techniques for editing large language models, and present new methods which can do so without requiring retraining. Our theoretical insights show that a single metric (a measure of the intrinsic dimension of t
Externí odkaz:
http://arxiv.org/abs/2406.12670
Autor:
Suzen, Neslihan, Mirkes, Evgeny M., Roland, Damian, Levesley, Jeremy, Gorban, Alexander N., Coats, Tim J.
Publikováno v:
2023 IEEE International Conference on Big Data (BigData), 4979-4986
Electronic patient records (EPRs) produce a wealth of data but contain significant missing information. Understanding and handling this missing data is an important part of clinical data analysis and if left unaddressed could result in bias in analys
Externí odkaz:
http://arxiv.org/abs/2402.06563
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
Autor:
Kastalskiy, Innokentiy, Zinovyev, Andrei, Mirkes, Evgeny, Kazantsev, Victor, Gorban, Alexander N.
Publikováno v:
Communications in Nonlinear Science and Numerical Simulation, Volume 132, May 2024, 107906
In the context of natural disasters, human responses inevitably intertwine with natural factors. The COVID-19 pandemic, as a significant stress factor, has brought to light profound variations among different countries in terms of their adaptive dyna
Externí odkaz:
http://arxiv.org/abs/2311.13917
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:
Bastounis, Alexander, Gorban, Alexander N., Hansen, Anders C., Higham, Desmond J., Prokhorov, Danil, Sutton, Oliver, Tyukin, Ivan Y., Zhou, Qinghua
In this work, we assess the theoretical limitations of determining guaranteed stability and accuracy of neural networks in classification tasks. We consider classical distribution-agnostic framework and algorithms minimising empirical risks and poten
Externí odkaz:
http://arxiv.org/abs/2309.07072
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
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:
Mirkes, Evgeny M, Bac, Jonathan, Fouché, Aziz, Stasenko, Sergey V., Zinovyev, Andrei, Gorban, Alexander N.
Publikováno v:
Entropy, 25(1), 33, 2023
Domain adaptation is a popular paradigm in modern machine learning which aims at tackling the problem of divergence (or shift) between the labeled training and validation datasets (source domain) and a potentially large unlabeled dataset (target doma
Externí odkaz:
http://arxiv.org/abs/2208.13290
Publikováno v:
Physics of Life Reviews, Volume 40, March 2022, Pages 15-23
In 1987, we analyzed the changes in correlation graphs between various features of the organism during stress and adaptation. After 33 years of research of many authors, discoveries and rediscoveries, we can say with complete confidence: It is useful
Externí odkaz:
http://arxiv.org/abs/2207.00330