%0 Journal Article %1 oladyshkin2023arbitrary %A Oladyshkin, Sergey %A Praditia, Timothy %A Kröker, Ilja %A Mohammadi, Farid %A Nowak, Wolfgang %A Otte, Sebastian %D 2023 %I Elsevier %J Neural networks %K %N September %P 85-104 %R 10.1016/j.neunet.2023.06.036 %T The deep arbitrary polynomial chaos neural network or how Deep Artificial Neural Networks could benefit from data-driven homogeneous chaos theory %V 166

@article{oladyshkin2023arbitrary, added-at = {2024-02-06T16:35:19.000+0100}, affiliation = {Oladyshkin, S (Corresponding Author), Univ Stuttgart, Inst Modelling Hydraul & Environm Syst, Stuttgart Ctr Simulat Sci, Dept Stochast Simulat & Safety Res Hydrosyst, Pfaffenwaldring 5a, D-70569 Stuttgart, Germany. Oladyshkin, Sergey; Praditia, Timothy; Kroeker, Ilja; Nowak, Wolfgang, Univ Stuttgart, Inst Modelling Hydraul & Environm Syst, Stuttgart Ctr Simulat Sci, Dept Stochast Simulat & Safety Res Hydrosyst, Pfaffenwaldring 5a, D-70569 Stuttgart, Germany. Mohammadi, Farid, Univ Stuttgart, Inst Modelling Hydraul & Environm Syst, Dept Hydromech & Modelling Hydrosyst, Pfaffenwaldring 61, D-70569 Stuttgart, Germany. Otte, Sebastian, Univ Tubingen, Comp Sci Dept, Neurocognit Modeling, Sand 14, D-72076 Tubingen, Germany.}, author = {Oladyshkin, Sergey and Praditia, Timothy and Kröker, Ilja and Mohammadi, Farid and Nowak, Wolfgang and Otte, Sebastian}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/20cb2a6b8777b68f85b76b2339957d887/unibiblio}, doi = {10.1016/j.neunet.2023.06.036}, interhash = {27def7cc3e277b0ff991e7725601e1b3}, intrahash = {0cb2a6b8777b68f85b76b2339957d887}, issn = {{0893-6080} and {1879-2782}}, journal = {Neural networks}, keywords = {}, language = {eng}, number = {September}, orcid-numbers = {Kroker, Ilja/0000-0003-0360-5307 Oladyshkin, Sergey/0000-0003-4676-5685}, pages = {85-104}, publisher = {Elsevier}, research-areas = {Computer Science; Neurosciences & Neurology}, timestamp = {2024-02-06T15:35:19.000+0100}, title = {The deep arbitrary polynomial chaos neural network or how Deep Artificial Neural Networks could benefit from data-driven homogeneous chaos theory}, unique-id = {WOS:001047798100001}, volume = 166, year = 2023 }