Papers
Published work.
Peer-reviewed work that uses the snn_opt framework, or provides background on the spiking-network methods underneath it. The list grows as additional applications reach publication.
- 2025 Application Biomimetics 10(12):808
Portfolio Optimization: A Neurodynamic Approach Based on Spiking Neural Networks
A. H. Khan, A. M. Mohammed, S. Li
Recasts the cardinality-constrained portfolio-selection problem as a constrained quadratic program and solves it with the spiking dynamics implemented in snn_opt. Demonstrates that SNN solutions match conventional convex solvers within numerical tolerance while exposing per-asset constraint activations as spike events — a diagnostic that classical solvers don't provide.
- 2025 Survey Artificial Intelligence Science and Engineering
Spiking Neural Networks: A Comprehensive Survey of Training Methodologies, Hardware Implementations and Applications
A. H. Khan et al.
Broader survey of SNN training methodologies and hardware platforms. Useful background reading for anyone entering the area; provides the wider context within which the SNN/QP equivalence sits.
In preparation
Additional applications of the framework — covering further classical machine-learning reductions and control problems — are at various stages of preparation and review. Entries will be added here as they appear in print.
Citing snn_opt
If snn_opt plays a role in your research or teaching,
please cite the software via the
CITATION.cff entry at the repository root, alongside
the relevant paper above when applicable.