Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Tyukin, I. Y."'
Publikováno v:
PLoS ONE 14(6): e0218304. 2019
Living neuronal networks in dissociated neuronal cultures are widely known for their ability to generate highly robust spatiotemporal activity patterns in various experimental conditions. These include neuronal avalanches satisfying the power scaling
Externí odkaz:
http://arxiv.org/abs/1812.09611
Publikováno v:
Information Sciences 466 (2018), 303-322
Artificial Intelligence (AI) systems sometimes make errors and will make errors in the future, from time to time. These errors are usually unexpected, and can lead to dramatic consequences. Intensive development of AI and its practical applications m
Externí odkaz:
http://arxiv.org/abs/1811.05321
Publikováno v:
Physics of Life Reviews Volume 29, July 2019, Pages 55-88
Despite the widely-spread consensus on the brain complexity, sprouts of the single neuron revolution emerged in neuroscience in the 1970s. They brought many unexpected discoveries, including grandmother or concept cells and sparse coding of informati
Externí odkaz:
http://arxiv.org/abs/1809.07656
The work concerns the problem of reducing a pre-trained deep neuronal network to a smaller network, with just few layers, whilst retaining the network's functionality on a given task The proposed approach is motivated by the observation that the aim
Externí odkaz:
http://arxiv.org/abs/1805.01516
Autor:
Gorban, A. N., Tyukin, I. Y.
Publikováno v:
Phil. Trans. R. Soc. A volume 376, issue 2118, 376 20170237, 2018
The concentration of measure phenomena were discovered as the mathematical background of statistical mechanics at the end of the XIX - beginning of the XX century and were then explored in mathematics of the XX-XXI centuries. At the beginning of the
Externí odkaz:
http://arxiv.org/abs/1801.03421
Autor:
Gorban, A. N., Tyukin, I. Y.
Publikováno v:
Neural Networks 94 (2017), 255-259
The problem of non-iterative one-shot and non-destructive correction of unavoidable mistakes arises in all Artificial Intelligence applications in the real world. Its solution requires robust separation of samples with errors from samples where the s
Externí odkaz:
http://arxiv.org/abs/1703.01203
We propose a new method to design adaptation algorithms that guarantee a certain prescribed level of performance and are applicable to systems with nonconvex parameterization. The main idea behind the method is, given the desired performance characte
Externí odkaz:
http://arxiv.org/abs/math/0309254
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.