Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computing

Jens E. Pedersen (), Steven Abreu, Matthias Jobst, Gregor Lenz, Vittorio Fra, Felix Christian Bauer, Dylan Richard Muir, Peng Zhou, Bernhard Vogginger, Kade Heckel, Gianvito Urgese, Sadasivan Shankar, Terrence C. Stewart, Sadique Sheik and Jason K. Eshraghian
Additional contact information
Jens E. Pedersen: KTH Royal Institute of Technology
Steven Abreu: University of Groningen
Matthias Jobst: Technische Universität Dresden
Gregor Lenz: Neurobus
Vittorio Fra: Politecnico di Torino
Felix Christian Bauer: SynSense
Dylan Richard Muir: SynSense
Peng Zhou: LuxiTech Co. Ltd.
Bernhard Vogginger: Technische Universität Dresden
Kade Heckel: University of Cambridge
Gianvito Urgese: Politecnico di Torino
Sadasivan Shankar: Stanford University
Terrence C. Stewart: National Research Council
Sadique Sheik: SynSense
Jason K. Eshraghian: University of California

Nature Communications, 2024, vol. 15, issue 1, 1-15

Abstract: Abstract Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for neural dynamics, there exists numerous software and hardware solutions and stacks whose variability makes it difficult to reproduce findings. Here, we establish a common reference frame for computations in digital neuromorphic systems, titled Neuromorphic Intermediate Representation (NIR). NIR defines a set of computational and composable model primitives as hybrid systems combining continuous-time dynamics and discrete events. By abstracting away assumptions around discretization and hardware constraints, NIR faithfully captures the computational model, while bridging differences between the evaluated implementation and the underlying mathematical formalism. NIR supports an unprecedented number of neuromorphic systems, which we demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms. NIR decouples the development of neuromorphic hardware and software, enabling interoperability between platforms and improving accessibility to multiple neuromorphic technologies. We believe that NIR is a key next step in brain-inspired hardware-software co-evolution, enabling research towards the implementation of energy efficient computational principles of nervous systems. NIR is available at neuroir.org

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-52259-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-52259-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-52259-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().