The inNuCE Research Infrastructure and the Neuromorphic MLOps for AIoT Prototyping
Authors:
- Gianvito UrgeseGianvito Urgese
- Vittorio FraVFVittorio Fra
- Andrea PignataAPAndrea Pignata
- Giuseppe FanuliGFGiuseppe Fanuli
- Walter Gallego GomezWGWalter Gallego Gomez
- Riccardo PignariRPRiccardo Pignari
- Michelangelo BarocciMBMichelangelo Barocci
- Benedetto LetoBLBenedetto Leto
- Paolo MontuschiPMPaolo Montuschi
- Enrico MaciiEMEnrico Macii
Open Access
- 11 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (9) , 19286-19299
Abstract
Neuromorphic computing promises significant improvements in latency and energy efficiency for machine intelligence at the edge. However, its adoption in the IoT domain is still limited by the heterogeneity of the hardware (HW), the immaturity of the toolchains, and the poor reproducibility of experiments. This article sets out the inNuCE research infrastructure (inNuCE RI), a two-pillar facility composed of a physical laboratory (inNuCE Lab) and a cloud-based heterogeneous prototyping platform (inNuCE HPP). The purpose of the inNuCE RI is to enable developers to prototype, evaluate, and compare neuromorphic and conventional end-to-end digital solutions. From a methodological perspective, we formalize the adaptation of machine learning operations (MLOps) to event-driven sensing and brain-inspired computation as neuromorphic MLOps (NMLOps). We illustrate how inNuCE RI instantiates NMLOps through containerized toolchains orchestrated with Kubernetes and Slurm-managed heterogeneous resources (neuromorphic chips, FPGAs, GPUs, and MCUs). The approach is analyzed on representative Artificial Intelligence of Things (AIoT) use cases, including human activity recognition (HAR), Braille reading, event-based gesture recognition, Hi-Co semantization of memories, navigation tracking, and constraint satisfaction problems. The development of inNuCE RI has been driven by the need to facilitate the transition from prototype (in nuce) to engineered AIoT systems for lower entry barriers and enforce reproducibility. This paves the way for future system-of-systems engineering.Keywords
Funding Information
- Italian National Recovery and Resilience Plan (NRRP), M4C2 through European Union–NextGenerationEU (IR0000011)
- Italian National Recovery and Resilience Plan (NRRP), M4C2 through European Union–NextGenerationEU (CUP B51E22000150006)
This publication has 49 references indexed in Scilit:
- Positioning and tracking enhancement through a spiking Legendre memory unitIFAC-PapersOnLine, 2025
- Variable-precision neuromorphic state space model for on-edge activity classificationFuture Generation Computer Systems, 2025
- Semantization of memories in a hippocampal–cortical spiking neural networkNeurocomputing, 2025
- Neu-BrAuER: A Neuromorphic Braille Letters Audio-Reader for Commercial Edge Devices2025
- Recent Advances in Artificial Sensory Neurons: Biological Fundamentals, Devices, Applications, and ChallengesNano-Micro Letters, 2024
- Automated machine learning: past, present and futureArtificial Intelligence Review, 2024
- MLOps Challenges in Industry 4.0SN Computer Science, 2023
- A Real-Time Rock-Paper-Scissor Hand Gesture Recognition System Based on FlowNet and Event Camera2019
- Event‐Based Neuromorphic Systems2014
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997