Dataset v1.0.0 CC BY 4.0

NeurOptimisation: The Spiking Way to Evolve

Experiment codes and datasets for the WCCI 2026 paper, featuring comprehensive experiments on BBOB test suite with linear and Izhikevich spiking neuron models.

GitHub Documentation Zenodo 📄 arXiv

Dataset Neuromorphic Optimisation Spiking Neural Networks Izhikevich Differential Evolution Evolutionary Computation BBOB

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

About This Dataset

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.

This dataset is a supplement to the preprint: arXiv:2507.08320

Datasets (1.0 GB total)

File	Description
`exconf.zip`	YAML configuration files used to launch each batch of experiments
`exdata-ioh.zip`	Resulting plots from experiments with IOHexperimenter
`exdata-coco.zip`	Raw results dataset generated using COCO platform (845.7 MB)
`ppdata-coco.zip`	Postprocessed datasets generated by `cocopp`
`exdata-time.zip`	Raw data for timing analysis and runtime scalability evaluation

Scripts

File	Description
`Example0.ipynb`	Simplest optimisation procedure using NeurOptimiser
`Example1.ipynb`	NeurOptimiser with default parameters on BBOB (IOH)
`Example2.ipynb`	NeurOptimiser with custom parameters on BBOB (COCO)
`exp_00-ioh.py`	Script for IOHexperimenter experiments
`exp_01-coco.py`	Script for COCO platform experiments
`exp_02-time.ipynb`	Timing analysis and runtime scalability evaluation

How to Use

The experiments can be reproduced using the provided scripts and configuration files:

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

Full Framework

The complete NeurOptimiser framework implementation is available at the GitHub repository.

Citation

@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},
}