deepsysid: System Identification Toolkit for Multistep Prediction using Deep Learning

DOI

deepsysid is a system identification toolkit for multistep prediction using deep learning and hybrid methods.

The toolkit is easy to use. After you follow the instructions in the README, you will be able to download a dataset, run hyperparameter optimization and identify your best-performing multistep prediction models with just three commands:

deepsysid download 4dof-sim-ship deepsysid session --enable-cuda progress.json NEW deepsysid session --enable-cuda --reportin=progress.json progress.json TEST_BEST

The most current version of this software is available on GitHub.

Identifier
DOI https://doi.org/10.18419/darus-3455
Metadata Access https://darus.uni-stuttgart.de/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.18419/darus-3455
Provenance
Creator Baier, Alexandra ORCID logo; Frank, Daniel ORCID logo
Publisher DaRUS
Contributor Baier, Alexandra
Publication Year 2023
Funding Reference DFG EXC 2075 - 390740016
Rights MIT License; info:eu-repo/semantics/openAccess; https://spdx.org/licenses/MIT.html
OpenAccess true
Contact Baier, Alexandra (Universität Stuttgart)
Representation
Resource Type Dataset
Format text/x-python; application/octet-stream; text/plain; charset=US-ASCII; application/json; text/markdown
Size 8400; 5559; 983; 1681; 7130; 2398; 35253; 10123; 1881; 14911; 10498; 3867; 4809; 50; 940; 142; 15623; 8494; 2333; 0; 16052; 5266; 10749; 1072; 7665; 8710; 501; 11946; 9007; 560; 7120; 17334; 16053; 43031; 110534; 1915; 1517; 8814; 63019; 22615; 1904; 10418; 21939; 5839; 3706; 11139; 2467; 5845; 2576; 1299; 17606; 1856; 858; 1627
Version 1.0
Discipline Construction Engineering and Architecture; Dynamical Systems; Engineering; Engineering Sciences; Mathematics; Natural Sciences