PN 6

SimTech EXC 2075 Project Network 6 "Machine learning for simulation"

Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

271 to 280 of 867 Results

LGBM-HPO_steps.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 107.9 GB - MD5: 63faf9208e0831c1eeda073b73302ccf DATA
main_no_results.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 555.1 MB - MD5: 9e1b8e3d2f905725b90fd498435245e4 DATA Benchmark results data for meta-train and meta-test benchmarks. Contains result summaries (enough for plotting) but not the detailed results.
main_results.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 260.5 GB - MD5: 147bd2b84a688a65e752a0b93af36424 DATA Detailed results, including predictions on datasets and best parameters, for all main methods. This excludes the data for individual hyperparameter optimization (HPO) steps, which is provided separately.
MLP-RTDL-HPO_steps.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 126.1 GB - MD5: 07ccbba1805898909d5c75df01fd847d DATA
pytabkit_code.zip Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data ZIP Archive - 6.9 MB - MD5: 80e03d81f1beb8a2173d5c38da4f493c Contains the code for running the meta-train and meta-test benchmarks, as well as an implementation of the models evaluated on these benchmarks. Also contains instructions in README.md as well as the documentation.
RealMLP-HPO_steps.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 128.6 GB - MD5: cecba6379df5f6ba81fcc51e7f087619 DATA
results_small.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 4.2 GB - MD5: 19babc91c7dab580a598551191da968b DATA Results folder (within the data folder) without extra results (predictions on the datasets, optimal hyperparameters).
tasks.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 3.1 GB - MD5: b224a117735d2e56bfd8c1546530a4c2 DATA Downloaded datasets, with restricted access for copyright reasons.
XGB-HPO_steps.tar.gz Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data Plain Text - 110.4 GB - MD5: e4671ada3b462010955e4da02dd9687c DATA
Data for: HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities Jul 8, 2024 - Hard Negative Captions Tilli, Pascal, 2024, "Data for: HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities", https://doi.org/10.18419/DARUS-4341, DaRUS, V1 Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image–text pairs, models fail to show fine-grained understanding of the combined semantics of these modalities. To this end, we propose Hard N...

LGBM-HPO_steps.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 107.9 GB -

DATA

main_no_results.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 555.1 MB -

DATA

Benchmark results data for meta-train and meta-test benchmarks. Contains result summaries (enough for plotting) but not the detailed results.

main_results.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 260.5 GB -

DATA

Detailed results, including predictions on datasets and best parameters, for all main methods. This excludes the data for individual hyperparameter optimization (HPO) steps, which is provided separately.

MLP-RTDL-HPO_steps.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 126.1 GB -

DATA

pytabkit_code.zip

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

ZIP Archive - 6.9 MB -

Contains the code for running the meta-train and meta-test benchmarks, as well as an implementation of the models evaluated on these benchmarks. Also contains instructions in README.md as well as the documentation.

RealMLP-HPO_steps.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 128.6 GB -

DATA

results_small.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 4.2 GB -

DATA

Results folder (within the data folder) without extra results (predictions on the datasets, optimal hyperparameters).

tasks.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 3.1 GB -

DATA

Downloaded datasets, with restricted access for copyright reasons.

XGB-HPO_steps.tar.gz

Aug 8, 2024 - Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Plain Text - 110.4 GB -

DATA

Data for: HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities

Jul 8, 2024 - Hard Negative Captions

Tilli, Pascal, 2024, "Data for: HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities", https://doi.org/10.18419/DARUS-4341, DaRUS, V1

Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image–text pairs, models fail to show fine-grained understanding of the combined semantics of these modalities. To this end, we propose Hard N...

Add Data

Share Dataverse

Link Dataverse

Reset Modifications