On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912340093435904 |
|---|---|
| author | Kröger, Lars Cioflan, Cristian Kartsch, Victor Benini, Luca |
| author_facet | Kröger, Lars Cioflan, Cristian Kartsch, Victor Benini, Luca |
| contents | RISC-V-based architectures are paving the way for efficient On-Device Learning (ODL) in smart edge devices. When applied across multiple nodes, ODL enables the creation of intelligent sensor networks that preserve data privacy. However, developing ODL-capable, battery-operated embedded platforms presents significant challenges due to constrained computational resources and limited device lifetime, besides intrinsic learning issues such as catastrophic forgetting. We face these challenges by proposing a regularization-based On-Device Federated Continual Learning algorithm tailored for multiple nano-drones performing face recognition tasks. We demonstrate our approach on a RISC-V-based 10-core ultra-low-power SoC, optimizing the ODL computational requirements. We improve the classification accuracy by 24% over naive fine-tuning, requiring 178 ms per local epoch and 10.5 s per global epoch, demonstrating the effectiveness of the architecture for this task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17436 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms Kröger, Lars Cioflan, Cristian Kartsch, Victor Benini, Luca Machine Learning Computer Vision and Pattern Recognition Multiagent Systems I.2.11; I.2.6; C.5.3; I.4.9 RISC-V-based architectures are paving the way for efficient On-Device Learning (ODL) in smart edge devices. When applied across multiple nodes, ODL enables the creation of intelligent sensor networks that preserve data privacy. However, developing ODL-capable, battery-operated embedded platforms presents significant challenges due to constrained computational resources and limited device lifetime, besides intrinsic learning issues such as catastrophic forgetting. We face these challenges by proposing a regularization-based On-Device Federated Continual Learning algorithm tailored for multiple nano-drones performing face recognition tasks. We demonstrate our approach on a RISC-V-based 10-core ultra-low-power SoC, optimizing the ODL computational requirements. We improve the classification accuracy by 24% over naive fine-tuning, requiring 178 ms per local epoch and 10.5 s per global epoch, demonstrating the effectiveness of the architecture for this task. |
| title | On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms |
| topic | Machine Learning Computer Vision and Pattern Recognition Multiagent Systems I.2.11; I.2.6; C.5.3; I.4.9 |
| url | https://arxiv.org/abs/2503.17436 |