Code and Data for: A Framework and Benchmark for Deep Batch Active Learning for Regression [arXiv v1] (doi:10.18419/darus-2615)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Code and Data for: A Framework and Benchmark for Deep Batch Active Learning for Regression [arXiv v1]

doi:10.18419/darus-2615

DaRUS

2022-04-13

1

Holzmüller, David; Zaverkin, Viktor; Kästner, Johannes; Steinwart, Ingo, 2022, "Code and Data for: A Framework and Benchmark for Deep Batch Active Learning for Regression [arXiv v1]", https://doi.org/10.18419/darus-2615, DaRUS, V1

Code and Data for: A Framework and Benchmark for Deep Batch Active Learning for Regression [arXiv v1]

doi:10.18419/darus-2615

Holzmüller, David (Universität Stuttgart)

Zaverkin, Viktor (Universität Stuttgart)

Kästner, Johannes (Universität Stuttgart)

Steinwart, Ingo (Universität Stuttgart)

EXC 2075 - 390740016

EXC 2075 - 390740016

DaRUS

Holzmüller, David

Holzmüller, David

Steinwart, Ingo

Holzmüller, David

2022-03-14

https://doi.org/10.18419/darus-2615

Computer and Information Science, Mathematical Sciences, Active Learning, Deep Learning, Artificial Neural Network, Regression

This dataset contains code and data for our paper <a href=https://arxiv.org/abs/2203.09410v1>"A Framework and Benchmark for Deep Batch Active Learning for Regression"</a>. The code can be used to reproduce the results, to benchmark new methods, or to apply the presented methods to new Deep Batch Active Learning problems. The code is also available on <a href=https://github.com/dholzmueller/bmdal_reg>GitHub</a>. Information on the code can be found in the file <a href="https://darus.uni-stuttgart.de/file.xhtml?fileId=102389">README.md</a> and in the Jupyter notebooks in the examples folder. Additionally, we provide the files <code>results.tar.gz</code> and <code>plots.tar.gz</code> which contain generated data and plots. These files can be unpacked in folders specified in <code>custom_paths.py</code> (see <a href="https://darus.uni-stuttgart.de/file.xhtml?fileId=102389">README.md</a>) and can be used as described in <code>examples/benchmark.ipynb</code>.

Basic instructions for installing and running the software can be found in the <a href="https://darus.uni-stuttgart.de/file.xhtml?fileId=102389">README.md</a> file.

<b>Dataset for arXiv v2:</b> <p>Holzmüller, David; Zaverkin, Viktor; Kästner, Johannes; Steinwart, Ingo, 2022, "Code and Data for: A Framework and Benchmark for Deep Batch Active Learning for Regression [arXiv v2]", doi:<a href="https://doi.org/10.18419/darus-3110">10.18419/darus-3110</a> , DaRUS, V1</p>

<b>Dataset for arXiv v3:</b> <p>Holzmüller, David; Zaverkin, Viktor; Kästner, Johannes; Steinwart, Ingo, 2022, "Code and Data for: A Framework and Benchmark for Deep Batch Active Learning for Regression [arXiv v3]", doi:<a href="https://doi.org/10.18419/darus-3394">10.18419/darus-3394</a> , DaRUS, V1</p>

David, Holzmüller, Viktor Zaverkin, Johannes Kästner, and Ingo Steinwart. A Framework and Benchmark for Deep Batch Active Learning for Regression, 2022.

2203.09410

David, Holzmüller, Viktor Zaverkin, Johannes Kästner, and Ingo Steinwart. A Framework and Benchmark for Deep Batch Active Learning for Regression, 2022.

Label:

check_task_learnability.py

text/x-python

Label:

custom_paths.py.default

application/octet-stream

Label:

data.py

text/x-python

Label:

data.tar.gz

Text:

Compressed folder containing downloaded raw and processed data sets as generated by download_data.py at the time of running the experiments.

application/gzip

Label:

download_data.py

text/x-python

Label:

layers.py

text/x-python

Label:

LICENSE

text/plain; charset=US-ASCII

Label:

models.py

text/x-python

Label:

NOTICE

text/plain; charset=US-ASCII

Label:

plots.tar.gz

Text:

Compressed folder containing all generated plots.

application/gzip

Label:

README.md

text/markdown

Label:

rename_algs.py

text/x-python

Label:

requirements.txt

text/plain

Label:

results.tar.gz

Text:

Compressed folder of experimental results generated by run_evaluation.py.

application/gzip

Label:

run_evaluation.py

text/x-python

Label:

run_experiments.py

text/x-python

Label:

task_execution.py

text/x-python

Label:

test_single_task.py

text/x-python

Label:

train.py

text/x-python

Label:

utils.py

text/x-python

Label:

algorithms.py

text/x-python

Label:

features.py

text/x-python

Label:

feature_data.py

text/x-python

Label:

feature_maps.py

text/x-python

Label:

layer_features.py

text/x-python

Label:

selection.py

text/x-python

Label:

__init__.py

text/x-python

Label:

analysis.py

text/x-python

Label:

plotting.py

text/x-python

Label:

visualize_lcmd.py

text/x-python

Label:

__init__.py

text/x-python

Label:

benchmark.ipynb

application/x-ipynb+json

Label:

framework_details.ipynb

application/x-ipynb+json

Label:

using_bmdal.ipynb

application/x-ipynb+json