NEC at WCCI 2026¶
Neuromorphic Evolutionary Computation¶
Abstract¶
Neuromorphic computing brings spiking dynamics and event-driven efficiency into the realm of optimisation. Evolutionary algorithms, long valued for their versatility, can now be re-imagined on this substrate. We first present the theoretical principles behind neuromorphic-based metaheuristics, highlighting their motivations, classification, and trade-offs. We then detail two neuromorphic evolutionary computation approaches: one includes a practical architecture in which units implement mutation and variation via spikes, and the other leverages the Basal-Ganglia-Thalamic loop. Finally, we discuss practical applications using open-source packages, showing participants how to design, run, and interpret neuromorphic optimisation experiments. This tutorial aims to demonstrate how spiking computation can shape a new generation of evolutionary search and open the way to applications in robotics, IoT, and embedded intelligence.
Learning Objectives¶
The main objective of this session is to equip participants with both conceptual and practical tools to understand and apply neuromorphic-based evolutionary computation algorithms.
In particular, by the end of the tutorial, participants will:
Understand the theoretical foundations of neuromorphic evolutionary optimisation.
Recognise the state-of-the-art architectures and their trade-off.
Learn from the authors the practical details and rationale for using and modifying the Neuroptimiser package to run experiments.
Identify research opportunities for scaling, hybridisation, and applications in WCCI’s fields.
Tutorial Outline¶
Introduction and Foundations (30 min) a. Metaheuristics and evolutionary computation basics b. Neuromorphic computing and spiking dynamics c. Theoretical framework of neuromorphic metaheuristics
Practical Framework: The NeurOptimiser (40 min)
a. Neuromorphic Heuristic Units and Spike-driven mutation strategies b. Hands-on exercises on benchmark functions from zero to hero c. Feasible adaptations and tweaks on the frameworkPerspectives and Future Directions (20 min)
Expected Audience¶
We anticipate 40-60 participants, mainly from CEC and IJCNN, and hope to include researchers from the FUZZ-IEEE scope to enrich the discussion during the session.
Important Dates¶
(31 January 2026)
Paper submission deadline (23h59, Anywhere On Earth, i.e., UTC-12).
No extension will be given!
(15 March 2026)
Paper acceptance notification
(15 April 2026)
Camera-ready papers
(21-26 June 2026)
IEEE WCCI 2026 @ Maastricht, NL: Tutorials (21 June), Industry Day (24 June), and Conference (22-26 June)
Tip
Further details can be found at the Official Website
Presenters¶
Jorge M. Cruz-Duarte is a Postdoctoral Researcher at the Equipe de Recherche Bonus, Centre Inria de l’Université de Lille. His research spans neuromorphic computing, metaheuristic optimisation, and automated algorithm design and configuration. He chairs the IEEE Computational Intelligence Society Task Force on Automated Algorithm Design, Configuration and Selection, and serves as an IEEE Computer Society Distinguished Visitor (2025-2027).
Email | Website | Google Scholar | DBLP
El-Ghazali Talbi is a full Professor at the University of Lille. His research interests include metaheuristics, computational intelligence, parallel and distributed optimisation, learning-based optimisation, and neuromorphic computing. He has authored more than 250 international publications, including journal and conference papers, and has delivered 52 keynotes and tutorials. With a h-index of 67 and over 24,000 citations, he is globally recognised for his contributions to computational intelligence and large-scale optimisation.
Email | Website | Google Scholar | DBLP