Zobrazeno 1 - 10
of 317
pro vyhledávání: '"Hamm, Thomas"'
Autor:
Hamm, Thomas
We present a derivation of the gradients of feedforward neural networks using Fr\'echet calculus which is arguably more compact than the ones usually presented in the literature. We first derive the gradients for ordinary neural networks working on v
Externí odkaz:
http://arxiv.org/abs/2209.13234
Autor:
Hamm, Thomas, Steinwart, Ingo
We prove minimax optimal learning rates for kernel ridge regression, resp.~support vector machines based on a data dependent partition of the input space, where the dependence of the dimension of the input space is replaced by the fractal dimension o
Externí odkaz:
http://arxiv.org/abs/2107.07750
Autor:
Hamm, Thomas, Steinwart, Ingo
We derive improved regression and classification rates for support vector machines using Gaussian kernels under the assumption that the data has some low-dimensional intrinsic structure that is described by the box-counting dimension. Under some stan
Externí odkaz:
http://arxiv.org/abs/2003.06202
Autor:
Hamm, Thomas
Die vorliegende Arbeit beschäftigt sich mit dem Vergleich der strahlendosisrelevanten Untersuchungsparameter zwischen einem Angiografiegerät mit BV und einem Angiografiegerät mit FD und 3D-Rotationsfunktion. Sie basiert auf 142 Angiografien der Ko
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A13037
https://ul.qucosa.de/api/qucosa%3A13037/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A13037/attachment/ATT-0/
Publikováno v:
SAE International Journal of Engines, 2014 Oct 01. 7(4), 1629-1636.
Externí odkaz:
https://www.jstor.org/stable/26277875
Autor:
Hamm, Thomas D
Publikováno v:
The Oxford International Encyclopedia of Peace, 1 ed., 2010.
Externí odkaz:
http://www.oxfordreference.com/view/10.1093/acref/9780195334685.001.0001/acref-9780195334685-e-602
Publikováno v:
In Journal of Theoretical Biology 21 November 2013 337:174-180
Publikováno v:
SAE International Journal of Engines, 2009 Jan 01. 1(1), 746-755.
Externí odkaz:
https://www.jstor.org/stable/26308317