Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Shinichi Nakajima"'
Autor:
Kristof T. Schütt, Jonas Lederer, Oliver Eberle, Shinichi Nakajima, Klaus-Robert Mueller, Grégoire Montavon, Thomas Schnake
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:7581-7596
Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explainable AI approaches are not applicable. To a large extent, GNNs have re
We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resulting path-gradient estimators are straightforward to implement, have l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c389de440f8607d0dc8df4f67294fd0
http://arxiv.org/abs/2207.08219
http://arxiv.org/abs/2207.08219
Autor:
Christopher J. Anders, Pan Kessel, Karl Jansen, Tobias Hartung, Shinichi Nakajima, Kim A. Nicoli, Paolo Stornati, Lena Funcke
Publikováno v:
Physical review letters 126(3), 032001 (1-6) (2021). doi:10.1103/PhysRevLett.126.032001
Physical Review Letters
Physical Review Letters
Physical review letters 126(3), 032001 (2021). doi:10.1103/PhysRevLett.126.032001
In this Letter, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Marko
In this Letter, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Marko
Autor:
Klaus-Robert Müller, Kim A. Nicoli, Wojciech Samek, Shinichi Nakajima, Nils Strodthoff, Pan Kessel
We propose a general framework for the estimation of observables with generative neural samplers focusing on modern deep generative neural networks that provide an exact sampling probability. In this framework, we present asymptotically unbiased esti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d2dbe03bbe27f36a5842a85db5249f3
http://arxiv.org/abs/1910.13496
http://arxiv.org/abs/1910.13496
Autor:
Alexander Bauer, Alexander Binder, Sebastian Lapuschkin, Shinichi Nakajima, Maximilian Kohlbrenner, Wojciech Samek
Publikováno v:
IJCNN
Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a39f51d5ae3d8f4b8ebe0e52c4560b08
http://arxiv.org/abs/1910.09840
http://arxiv.org/abs/1910.09840