Data

Tools

Indexes

Applications

Experiments

Open Source Science

into-the-unknown-extended

Active monitoring of neural networks (extended version)

https://github.com/verixai/into-the-unknown-extended

Science Score: 41.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 3 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.5%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Active monitoring of neural networks (extended version)

Basic Info
  • Host: GitHub
  • Owner: VeriXAI
  • Language: Python
  • Default Branch: master
  • Size: 6.32 MB
Statistics
  • Stars: 0
  • Watchers: 4
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 4 years ago · Last pushed over 2 years ago
Metadata Files
Readme Citation

README.md

Into the Unknown (Extended)

This repository contains the implementation and data used in the paper "Into the Unknown: Active Monitoring of Neural Networks (Extended)". To cite the work, you can use:

@article{KueffnerLSH23, author = {Konstantin Kueffner and Anna Lukina and Christian Schilling and Thomas A. Henzinger}, title = {Into the unknown: active monitoring of neural networks (extended version)}, journal = {Int. J. Softw. Tools Technol. Transf.}, volume = {25}, number = {4}, pages = {575--592}, publisher = {Springer}, year = {2023}, url = {https://doi.org/10.1007/s10009-023-00711-4}, doi = {10.1007/S10009-023-00711-4} }

Installation

You need Python 3.7 or 3.6. For newer Python versions, the packages have to be updated. The package requirements that need to be installed are found in the file requirements.txt.

Since the datasets are large and have mostly been used in our previous work, we do not include most of them here. You need to manually download them (see the links below) and extract them to the data folder of this repository.

Modify the file called paths.txt in the base folder, which contains two lines that are the paths to the model and dataset folders:

.../models/ .../data/

Here replace the ... with the absolute path to your clone of the repository.

Links to dataset files

  • MNIST
  • Fashion MNIST
  • GTSRB (You need to manually extract the file train.zip because the content is too large for GitHub.)

Recreation of the results

To obtain the results from the conference version of the paper Into the Unknown: Active Monitoring of Neural Networks, published at RV 2021, see this repository.

Below we describe how to obtain the results shown in section 7.3 of the journal version of the paper. The results of those experiments will be output to the directory experiment_data.

Reproduce the Experiment

To generate the models and the data used in the experiments, run run/train_experiment_into_the_unknown_extended.py.

Evaluation

To reproduce the figures found in section 7.3 of the paper, run run/run_experiment_into_the_unknown_extended.py.

Owner

  • Name: VeriXAI
  • Login: VeriXAI
  • Kind: organization

Citation (CITATION.bib) 

@article{KueffnerLSH23,
  author       = {Konstantin Kueffner and
                  Anna Lukina and
                  Christian Schilling and
                  Thomas A. Henzinger},
  title        = {Into the unknown: active monitoring of neural networks (extended version)},
  journal      = {Int. J. Softw. Tools Technol. Transf.},
  volume       = {25},
  number       = {4},
  pages        = {575--592},
  publisher    = {Springer},
  year         = {2023},
  url          = {https://doi.org/10.1007/s10009-023-00711-4},
  doi          = {10.1007/S10009-023-00711-4}
}

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Dependencies

requirements.txt pypi
  • albumentations *
  • dd *
  • eagerpy *
  • foolbox ==3.0.0b1
  • h5py *
  • keras ==2.4.3
  • matplotlib *
  • numpy *
  • pandas *
  • plotly *
  • pypoman *
  • scikit-image *
  • scikit-learn *
  • scipy ==1.4.1
  • seaborn *
  • sklearn *
  • tensorflow ==2.2.0