NeurOptimisation: The Spiking Way to Evolve - Experiment Codes and Dataset

This repository contains datasets and scripts generated from experiments conducted with the NeurOptimiser framework, as described in related publication(s).

Please refer to the publication that cites this dataset for detailed descriptions of the experimental protocols and results.

About This Repository

This Zenodo repository serves exclusively for reproducibility, providing:

• Raw experimental data from all performed benchmark runs.
• Experimental configurations and parameter files.
• Scripts and processing routines used to generate the experimental figures and tables reported in the paper.

The comprehensive experiments assess the functionality, scalability, and runtime performance of the NeurOptimiser framework across the BBOB test suite, utilising both linear and Izhikevich spiking neuron models. Nevertheless, the information provided here can be easily adapted to other neuromorphic optimisation algorithms and problems.

Note that this repository does not include the full NeurOptimiser framework implementation, which is available in the main GitHub repository linked below.

Full Framework Repository

The complete NeurOptimiser framework, including its implementation, source code, and latest releases, is hosted at:

https://github.com/neuroptimiser/neuroptimiser

Its documentation can be found at:

https://neuroptimiser.github.io/

What is inside this Zenodo Repository?

This repository is organised into two main components: datasets and scripts.

Datasets

• exconf.zip: YAML configuration files used to launch each batch of experiments.
• exdata-ioh.zip: Resulting plots from experiments conducted using exp_00-ioh.py, which implements the BBOB test suite from IOHexperimenter.
• exdata-coco.zip: Raw results dataset generated using exp_01-coco.py script along with the exp_01-coco-*.yaml configuration files from exconf.zip.
• ppdata-coco.zip: Postprocessed datasets generated by cocopp from COCO platform employing the raw results from exdata-coco.zip.
• exdata-time.zip: Raw data for timing analysis and runtime scalability evaluation, generated by exp_01-coco.py with the time_*.yaml configuration files from exconf.zip.

Scripts

• Example0.ipynb: Jupyter notebook showing how to implement the simplest optimisation procedure using the NeurOptimiser framework.
• Example1.ipynb: Jupyter notebook showing how to implement a neuroptimiser, using default parameters, to solve a BBOB problem from IOH.
• Example2.ipynb: Jupyter notebook showing how to implement a neuroptimiser, using different parameters, to solve a BBOB problem from COCO.
• exp_00-ioh.py: Script to run the experiments and generate the raw data and plots from experiments with IOHexperimenter. Results are saved in exdata-ioh.zip.
• exp_01-coco.py: Script to run the experiments and generate raw data and plots from experiments with COCO. Raw and postprocessed results are saved in exdata-coco.zip and ppdata-coco.zip, respectively. This script requires YAML configuration files from exconf.zip to run the experiments.

  python exp_01-coco.py ./exconf/toy.yaml 1 1 
  # Args: <config_file> <num_batches> <batch>

• exp_02-time.ipynb: Jupyter notebook for timing analysis and runtime scalability evaluation. The raw data used in this notebook is saved in exdata-time.zip, which was generated also with the exp_01-coco.py and with the time_*.yamlconfiguration files in exconf.zip.

Related Publication

The experiments associated with this dataset are described in scientific publications that reference this dataset. Please refer to the corresponding publication for detailed methodology and results.

How to Reference this Dataset

IEEE

J. M. Cruz-Duarte and E.-G. Talbi, "NeurOptimisation: The Spiking Way to Evolve - Experiment Codes and Dataset," Zenodo, version 1.0.0, 2025. DOI: 10.5281/zenodo.15858610.

APA

Cruz-Duarte, J. M., & Talbi, E.-G. (2025). NeurOptimisation: The Spiking Way to Evolve - Experiment Codes and Dataset (1.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.15858610

MLA

Cruz-Duarte, J. M.and E.-G. Talbi. NeurOptimisation: The Spiking Way to Evolve - Experiment Codes and Dataset. 1.0.0, Zenodo, 10 July 2025, doi:10.5281/zenodo.15858610.

BibTeX

@dataset{Cruz2025neuroptimiser-dataset,
    author       = {Cruz-Duarte, Jorge M. and Talbi, El-Ghazali},
    title        = {NeurOptimisation: The Spiking Way to Evolve - Experiment Codes and Dataset},
    month        = jul,
    year         = 2025,
    publisher    = {Zenodo},
    version      = {1.0.0},
    doi          = {10.5281/zenodo.15858610},
    url          = {https://doi.org/10.5281/zenodo.15858610},
}

License

This dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. The full NeurOptimiser framework is distributed under its own license in the main GitHub repository.

Contact

For questions or collaborations:

• Jorge M. Cruz-Duarte, jorge.cruz-duarte@univ-lille.fr
• El-Ghazali Talbi, el-ghazali.talbi@univ-lille.fr

This Zenodo repository contains only experimental material. Users interested in using or extending the NeurOptimiser framework should refer to the main repository above.