Scalable network emulation on analog neuromorphic hardware
We present a novel software feature for the BrainScaleS-2 accelerated neuromorphic platform that facilitates the partitioned emulation of large-scale spiking neural networks. This approach is well suited for deep spiking neural networks and allows for sequential model emulation on undersized neuromo...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
05 February 2025
|
| In: |
Frontiers in neuroscience
Year: 2024, Jahrgang: 18, Pages: 1-10 |
| ISSN: | 1662-453X |
| DOI: | 10.3389/fnins.2024.1523331 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.3389/fnins.2024.1523331 Verlag, kostenfrei, Volltext: https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1523331/full 
|
| Verfasserangaben: | Elias Arnold, Philipp Spilger, Jan V. Straub, Eric Müller, Dominik Dold, Gabriele Meoni and Johannes Schemmel |
| Zusammenfassung: | We present a novel software feature for the BrainScaleS-2 accelerated neuromorphic platform that facilitates the partitioned emulation of large-scale spiking neural networks. This approach is well suited for deep spiking neural networks and allows for sequential model emulation on undersized neuromorphic resources if the largest recurrent subnetwork and the required neuron fan-in fit on the substrate. We demonstrate the training of two deep spiking neural network models - using the MNIST and EuroSAT datasets - that exceed the physical size constraints of a single-chip BrainScaleS-2 system. The ability to emulate and train networks larger than the substrate provides a pathway for accurate performance evaluation in planned or scaled systems, ultimately advancing the development and understanding of large-scale models and neuromorphic computing architectures. |
|---|---|
| Beschreibung: | Gesehen am 03.12.2025 |
| Beschreibung: | Online Resource |
| ISSN: | 1662-453X |
| DOI: | 10.3389/fnins.2024.1523331 |