EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Parallelized Hierarchical Connectome: A spatiotemporal recurrent framework for spiking state-space models

Po-Han Chiang

Array · 2026-12 · 32 · 101315

DOI: 10.1016/j.array.2026.101315 ↗

At a glance

Journal article in Array, 2026-12. Written by Po-Han Chiang. 69 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Science and Technology Council.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

This work presents the Parallelized Hierarchical Connectome (PHC), a general architectural framework that upgrades temporal-only State-Space Models (SSMs) into spatiotemporal recurrent networks. Conventional SSMs achieve parallel-scan training but are limited to temporal recurrence, lacking lateral or feedback interactions within a single timestep. PHC maps the diagonal SSM core to a shared Neuron Layer and inter-neuronal communication to a shared Synapse Layer of hierarchical regions, reconnected by a Multi-Transmission Loop iterating spatial recurrence within each temporal window, at parameter complexity Theta(D^2) versus Theta(D^2 L) of stacked SSMs. This spatiotemporal framework enables the seamless integration of neuro-physical priors typically intractable for standard SSMs, including adaptive LIF, synaptic delay, STP, Dale's Law with E/I-asymmetric topology, and STDP. The framework is instantiated as PHCSSM, the first spiking SSM that integrates all five biological priors and is evaluated on long-sequence data, achieving test accuracy competitive with state-of-the-art SSM baselines at 1,312 to 4,891 trainable parameters (1 to 4 orders of magnitude smaller than every baseline). PHCSSM further admits a sequential recurrent spiking neural network (RSNN) deployment mode that converges asymptotically to the parallel-scan training mode without artificial-neural-network-to-spiking-neural-network (ANN-to-SNN) conversion, with cross-backend reproducibility verified across four hardware backends (x86 CPU, H100 GPU, Cortex-A76, Cortex-M4F) including end-to-end deployment on the Cortex-M4F microcontroller (40 KB SRAM, 128 KB Flash). PHCSSM thereby bridges parallel-scan SSM and biologically grounded RSNN, two paradigms with previously incompatible training regimes, into a single architecture and trained weights.

Funding

  • National Science and Technology Council

Cite

APA

Chiang, P. (2026). Parallelized Hierarchical Connectome: A spatiotemporal recurrent framework for spiking state-space models. Array, 32, 101315. https://doi.org/10.1016/j.array.2026.101315

Vancouver

Chiang P. Parallelized Hierarchical Connectome: A spatiotemporal recurrent framework for spiking state-space models. Array. 2026;32:101315. doi:10.1016/j.array.2026.101315

BibTeX
@article{Chiang2026,
  author = {Chiang, Po-Han},
  title = {Parallelized Hierarchical Connectome: A spatiotemporal recurrent framework for spiking state-space models},
  journal = {Array},
  year = {2026},
  volume = {32},
  pages = {101315},
  doi = {10.1016/j.array.2026.101315}
}
Start for free →